major(llm): Support Embedding Providers

Refactor LLM provider system and introduce GUI for simulations

.github/workflows/deploy-docs.yml

@@ -0,0 +1,44 @@
+name: Deploy Docs
+
+on:
+  push:
+    branches:
+      - master
+    paths:
+      - 'web/docs/**'
+      - 'pnpm-lock.yaml'
+      - '.github/workflows/deploy-docs.yml'
+  workflow_dispatch:
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    name: Deploy Docs to Cloudflare Workers
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 11
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+          cache: 'pnpm'
+
+      - name: Install Dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Build Docs
+        run: pnpm --filter docs build
+
+      - name: Deploy to Cloudflare Workers
+        uses: cloudflare/wrangler-action@v3
+        with:
+          apiToken: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+          accountId: ${{ secrets.CLOUDFLARE_ACCOUNT_ID }}
+          workingDirectory: 'web/docs'

CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+- Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+- The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+mail@adityagupta.dev.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

CONTRIBUTING.md

@@ -0,0 +1,99 @@
+# Contributing to Omnia
+
+Thank you for your interest in contributing to Omnia! We welcome contributions from developers, technical writers, and anyone interested in agentic narrative simulation.
+
+Please take a moment to review this document before submitting contributions.
+
+## Table of Contents
+
+1. [Documentation](#documentation)
+2. [Getting Started](#getting-started)
+3. [Development Workflow](#development-workflow)
+4. [Coding Standards](#coding-standards)
+5. [Pull Request Guidelines](#pull-request-guidelines)
+
+## Documentation
+
+The primary source of truth for the Omnia project is the official documentation:
+👉 **[Omnia Documentation](https://omnia.adityagupta.dev/docs)**
+
+Please refer to the documentation to understand the project architecture, memory model, spatial systems, intents framework, and custom LLM configurations.
+
+## Getting Started
+
+Omnia is organized as a monorepo managed with **pnpm** workspaces.
+
+### Prerequisites
+
+- **Node.js** (v22.13 or newer recommended)
+- **pnpm** (v11 or newer recommended)
+
+### Local Setup
+
+1. Fork the repository and clone your fork:
+   ```bash
+   git clone https://github.com/YOUR_USERNAME/omnia-consolidated.git
+   cd omnia-consolidated
+   ```
+2. Install dependencies:
+   ```bash
+   pnpm install
+   ```
+3. Run the Web GUI interface locally:
+   ```bash
+   pnpm dev:gui
+   ```
+4. Run the Starlight documentation site locally:
+   ```bash
+   pnpm dev:docs
+   ```
+
+## Development Workflow
+
+### Branching
+
+Create a descriptive branch for your changes:
+
+```bash
+git checkout -b feature/your-feature-name
+# or
+git checkout -b fix/issue-description
+```
+
+### Running Tests
+
+Make sure all unit tests pass before submitting changes:
+
+```bash
+# Run tests once
+pnpm test
+
+# Run tests in watch mode
+pnpm test:watch
+```
+
+### Linting and Formatting
+
+We enforce consistent code quality and formatting rules across the repository.
+
+```bash
+# Check code style and formatting
+pnpm lint
+pnpm format:check
+
+# Auto-fix code style issues
+pnpm lint:fix
+pnpm format
+```
+
+## Coding Standards
+
+- **TypeScript**: Omnia is written entirely in TypeScript. Ensure all new code is strongly typed.
+- **Docstrings**: Document public-facing APIs, methods, and configurations.
+
+## Pull Request Guidelines
+
+1. **Keep PRs Focused**: Keep your changes as small and focused as possible.
+2. **Include Tests**: If you are introducing a new feature or fixing a bug, write corresponding tests in `tests/`.
+3. **Update Documentation**: If your changes alter public behavior or introduce new APIs, update the docs under `web/docs/src/content/docs/`.
+4. **Follow Commit Conventions**: Write clear, descriptive commit messages.

README.md

@@ -1,49 +1,97 @@
-![Omnia Logo](web/docs/src/assets/img/logo.png)
+<p align="center">
+<img src="web/docs/src/assets/img/logo.png" alt="Omnia Logo" />
+</p>
 
-An LLM-assisted narrative simulation engine where the <b>world state lives outside the model</b>, characters act through <b>intents that get validated</b> and applied by engine code, and each character's knowledge, memory, and emotional state are subjective and partial by construction.
+<h1 align="center">Omnia</h1>
 
-Omnia is an engine for building narrative RPG-style worlds where characters are played by a language model. It is built to survive long play sessions instead of falling apart after twenty minutes.
+<p align="center">
+<b>An architectural framework for multi agent-narrative simulations and fictional worlds!</b>
+</p>
+<p align="center">
+  <a href="https://omnia.adityagupta.dev/docs"><img src="https://img.shields.io/badge/Omnia_Docs-Read_The_Docs-red?style=for-the-badge" alt="Docs" /></a>
+  <img src="https://img.shields.io/github/license/sortedcord/omnia-consolidated?style=for-the-badge" alt="License" />
+  <img src="https://img.shields.io/github/repo-size/sortedcord/omnia-consolidated?style=for-the-badge" alt="Repo Size" />
+  <img src="https://img.shields.io/github/languages/top/sortedcord/omnia-consolidated?style=for-the-badge" alt="Top Language" />
+</p>
 
-## The Problem with the Naive Approach
+The <b>world state lives outside the model</b>, characters act through <b>intents that get validated</b> and applied by engine code. Each character's knowledge, memory, and emotional state are subjective and partial by construction.
 
-Single-agent, single-context systems (AI Dungeon and its descendants) prompt one model to _be_ the world and everyone in it. That breaks in predictable ways over long sessions:
+<p align="center">
+  <img src="./web/docs/src/assets/img/puppet.webp" />
+</p>
 
-- **State Leaks:** Characters know things they had no way of learning, because a model with full context cannot help but use it. The assassin's target greets him by name.
-- **Secrets Refuse to Stay Secret:** "Don't reveal this" is a suggestion a model can argue past, not a mechanism that says no. One clever player question and the conspiracy folds.
+Single-agent or single-context systems (AI Dungeon and its descendants) prompt one model to _be_ the world and everyone in it. That breaks in predictable ways over long sessions:
+
+- **State Leaks:** Characters know things they had no way of learning, because a model with full context cannot help but use it.
 - **Consequences Evaporate:** Betray someone, apologize, and they forgive you a turn later because nothing is tracking the betrayal as a persistent fact.
-- **Emotional Drift:** Emotional state is either frozen into a meaningless number (`trust: 40`) or handed to the model to grade itself, producing drifting, arbitrary values.
+- **Stat Drift:** Statistical attributes are either frozen into a meaningless number (`trust: 40`) or handed to the model to grade itself, producing drifting, arbitrary values.
 - **World Rot:** The world state slowly contradicts itself because the model has no structured place to keep it. The locked door is open, then locked, then never existed.
-- **Everyone Is One Person:** Every character shares one context, so every character shares one mind. They can't genuinely surprise each other, lie to each other, or know different things — they're sock puppets on the same hand.
+- **Everyone Is One Person:** Every character shares one context, so every character shares one mind. They can't genuinely surprise each other, lie to each other, or know different things. They're sock puppets on the hands of one puppetmaster.
 
-The root cause is the same in every case: the model is being asked to be the database, the physics engine, the referee, and the whole cast simultaneously — inside a context window that forgets, blends, and leaks.
+The model should not be the database, the physics engine and the whole cast simultaneously inside a sliding context window.
 
 ## The Omnia Solution
 
-Omnia answers every one of these failures with the same move: pull the thing that has to stay consistent out of the model and into structured, queryable, code-controlled state.
+Omnia answers every one of these failures with the same move: **pull the thing that has to stay consistent out of the model** and into structured, queryable, code-controlled state.
 
-- **World State:** Lives in a SQLite database, not in a context window. It cannot drift, because nothing regenerates it — it only changes through validated deltas.
+- **World State:** Lives in a DB, not a context window. It cannot drift, because nothing regenerates it. The world state only changes through validated deltas.
 - **Actions:** Actions are proposals (Intents) that engine code validates and applies; they are never direct edits the model makes to the world. The model proposes; deterministic code disposes.
-- **Epistemic Privacy:** Knowledge, memory, and emotion are modeled per character and kept partial on purpose. A character literally cannot reach for what it has not earned the right to know — the secret is not in its prompt, so there is nothing to jailbreak out of it.
+- **Epistemic Privacy:** Knowledge, memory, and emotion are modeled per character and kept partial on purpose. A character literally cannot reach for what it has not earned the right to know. The secret is not in its prompt, so there is **nothing to jailbreak out of it**.
 
-## What This Buys You
+## What this buys you
 
-The payoff is scenario complexity that uni-agent systems structurally cannot represent, no matter how good the model gets:
+<p align="center">
+  <img src="./web/docs/src/assets/img/features.webp" />
+</p>
+
+The payoff is scenario complexity that **uni-agent systems structurally cannot represent, no matter how good the model gets**.
 
 - **Real secrets, real dramatic irony.** One NPC knows the sword is cursed; the other does not. This holds for hundreds of turns not because the model is disciplined, but because the second NPC's prompts are constructed from an attribute set that simply does not contain the fact. Leaking it would require the engine to have handed it over.
-- **Genuine deception between characters.** Because each character acts from its own bounded view, characters can lie to each other — and be believed — with the truth intact in the world state. A con game, a mole in the party, an unreliable ally: these are queries over who-knows-what, not prompt acrobatics.
-- **Betrayal that stays betrayed.** Events persist as per-observer memory entries with outcomes. An apology adds a memory; it does not delete one.
-- **Divergent accounts of the same event.** Two witnesses to the same scene hold two different buffer entries, filtered through their own aliases and vantage points. Ask them separately what happened and you get testimony, not a transcript.
-- **Identity as information.** Characters refer to each other through subjective alias maps ("the hooded figure" vs. "Bob"). Recognizing someone, being recognized, or staying anonymous are all mechanical states — a masked stranger is a masked stranger until the engine says otherwise.
-- **A physics referee that can say no.** "I pick the lock with a hairpin" is validated against world state by the Architect before anything changes. Failure is a recorded outcome the character remembers, not a narrative the model politely retconned.
-- **Time that behaves.** A world clock advances by validated, per-action deltas, and memory is recalled with psychologically natural phrasing ("earlier today, in the afternoon" — not a timestamp). Long timelines stay coherent because time is data, not vibes.
+- **Genuine deception between characters.** Because each entity acts from its own bounded view, they can lie to each other and be believed; with the truth intact in the world state. A con game, a mole in the party, an unreliable ally: these are queries over "who knows what" and not prompt engineering.
+- Events persist as per observer memory entries with outcomes. An apology adds a memory; it does not delete one.
+- **Divergent accounts of the same event.** Two witnesses to the same scene hold two different buffer entries, filtered through their own aliases and vantage points. Ask them separately what happened and you get varied testimony.
+- **A physics referee that can say no.** `I pick the lock with a hairpin` is validated against world state by the Architect before anything changes. Failure is a recorded outcome the entity remembers.
+- **Time that behaves.** A world clock advances by validated, per-action deltas, and memory is recalled with psychologically natural phrasing ("earlier today, in the afternoon" — not a timestamp). `TimeOfDay` is deterministic and not based on vibes.
+- **No main character syndrome.** The simulation runs fully autonomously or you act on behalf of any entity. You, the player, are just an entity in the data model, not structurally elevated above the rest of the world. The world can exist without the you.
+- **Granular model control.** Omnia is not locked to a single LLM. You can pick a different model for **every individual step that calls the LLM**. Narration prose that demands richer reasoning gets a frontier model; quick intent decoding or other generators get smaller ones or a model running entirely on your local machine.
 
-The general principle: **anything that must remain true is state; the model only ever supplies behavior.** That division of labor is what lets the cast, the secrets, and the timeline scale without the fiction collapsing.
+The general principle: **anything that must remain true is state; the model only ever supplies behavior.**
+
+## Installation
+
+### Prerequisites
+
+- [Node.js](https://nodejs.org/) (v20+ recommended)
+- [pnpm](https://pnpm.io/) (v9+ recommended)
+- An API key for Google Gemini (`GOOGLE_API_KEY` environment variable), or configured settings via the GUI.
+
+### Installation
+
+1. Clone the repository:
+   ```bash
+   git clone https://github.com/sortedcord/omnia-consolidated.git
+   cd omnia-consolidated
+   ```
+2. Install dependencies:
+   ```bash
+   pnpm install
+   ```
+
+### Running the Web GUI
+
+To launch the Next.js development server for the GUI dashboard:
+
+```bash
+pnpm dev:gui
+```
+
+Access the application locally at `http://localhost:3000`.
 
 ## Core Architecture
 
 ### The Actor Agent
 
-Each character takes turns through an **Actor Agent** that receives a strictly epistemically-bounded prompt: its own attributes (public, plus private ones explicitly granted to itself), its subjective memory buffer, the entities co-present at its location, and the current moment. Nothing else. The actor responds with free narrative prose — what the character does, says, or _thinks_.
+Each entity takes turns through an **Actor Agent** that receives a strictly epistemically bounded prompt: its own attributes (public, plus private ones explicitly granted to itself), its subjective memory buffer, the entities co-present at its location, and the current moment. Nothing else. The actor responds with free narrative prose.
 
 Prose is decoded into typed intents:
 
@@ -51,29 +99,29 @@ Prose is decoded into typed intents:
 - **`action`** — a physical act, subject to validation.
 - **`monologue`** — an inner thought. No one else perceives it, it bypasses validation entirely, and it is written straight into the character's private memory.
 
-Not every turn needs an outward act; a character may simply think. This is what makes characters feel inhabited rather than reactive — and it produces a durable, queryable record of each character's private reasoning (see [Research Instrument](#a-research-instrument-model-psychology-in-fiction) below).
+Not every turn needs an outward act; a character may simply think. This is what makes characters feel inhabited rather than reactive and it produces a queryable record of each character's private reasoning (see [Research Instrument](#a-research-instrument-model-psychology-in-fiction) below).
 
-The prose generator is pluggable (`IActorProseGenerator`): the same turn loop runs an LLM-driven NPC or a human at a CLI prompt, identically bounded by what their character knows.
+The prose generator is pluggable (`IActorProseGenerator`): the same turn loop runs an LLM driven NPC or a human, identically bounded by what their character knows. (This is what eliminates Main Character Syndrome)
 
 ### Intents & The World Architect
 
-An action becomes an **Intent** — a cheap, declarative, allowed-to-be-wrong proposal. Intents route to the **World Architect**, which validates them against the objective world state (dialogue is exempt; monologue never even arrives) and generates structured deltas — starting with time advancement — that deterministic code applies after strict schema (Zod) validation. The model proposes a change; it never touches the database.
+An action becomes an **Intent** which is a simple proposal that is _allowed to be wrong_. Intents route to the **World Architect**, which validates them against the objective world state and generates structured deltas like time advancement, attribute change, etc. This deterministic code applies after strict schema (Zod) validation. The model never touches the DB.
 
-This is the load-bearing wall. Because every mutation flows through one validated chokepoint, the world cannot rot: there is no second copy of reality inside a context window to fall out of sync.
+Because every mutation flows through one validated chokepoint, the world cannot rot: there is no second copy of reality inside a context window to fall out of sync.
 
-### Attribute-Level Privacy
+### Attribute Level Privacy
 
-Every entity, item, and location is an attribute bag. Each attribute carries its own visibility (`PUBLIC` or `PRIVATE`) with an explicit access list. "The sword is cursed" is a private attribute checked in code, not a rule the model is politely asked to honor. Privacy lives at the level of the fact, not the entity — a character can be publicly a blacksmith and privately a spy, and even facts about _itself_ are hidden from it unless explicitly granted (amnesia, repression, and unwitting sleeper agents come free with the model).
+Every entity, item, and location is an _attribute bag_. Each attribute carries its own visibility (`PUBLIC` or `PRIVATE`) with an explicit access list. "The sword is cursed" is a private attribute checked in code, not a rule the model is politely asked to honor. Privacy lives at the level of the fact, not the entity. A character can be publicly a blacksmith and privately a spy, and even facts about _itself_ are hidden from it unless explicitly granted (amnesia, repression, and unwitting sleeper agents come free with the model).
 
 The dividend: **prompt-injection-proof secrets.** There is no instruction to override because the information was never serialized into the prompt. Epistemic privacy turns "the model shouldn't say this" (hard, unreliable) into "the model doesn't know this" (trivial, absolute).
 
 ### Spatial Perception
 
-Space is a graph: `world → region → location → point of interest`, connected by portals with sound and vision propagation values. When something happens, it bubbles outward. There are no coordinates, no pathfinding, no collision geometry — a narrative engine doesn't need a tactical simulation, and a discrete graph is sufficient. Today actors perceive co-located entities and their location's visible attributes; portal-propagated perception is on the roadmap.
+Space is a graph: `world → region → location → point of interest`, connected by portals with sound and vision propagation values. When something happens, it bubbles outward. There are no coordinates, no pathfinding, no collision geometry — a narrative engine doesn't need a tactical simulation, and a discrete graph is sufficient. Today actors perceive co-located entities and their location's visible attributes; portal propagated perception is on the roadmap.
 
 ### Memory Tiers
 
-- **Verbatim Buffer (implemented):** Per-character subjective event log. Every entry is stored from the owner's perspective — actors resolved through the owner's alias map, outcomes attached — and recalled with naturalized time phrasing.
+- **Verbatim Buffer (implemented):** Per-character subjective event log. Every entry is stored from the owner's perspective actors resolved through the owner's alias map, outcomes attached — and recalled with naturalized time phrasing.
 - **Vector Archive (planned):** Summarized, embedded memory entries for semantic retrieval, keeping verbatim quotes only for high-salience lines.
 - **Dossier (planned):** Each observer's subjective beliefs about another character.
 
@@ -83,16 +131,20 @@ Memory is per-character on purpose: recall is testimony from a vantage point, wh
 
 Rather than a scalar the model drifts, every significant interaction becomes a ledger entry with an affect vector across OCC-derived dimensions (plus arousal, dominance, and social drive). The model judges a single moment; deterministic code aggregates the ledger over time with decay and attention weighting. A character can be simultaneously furious about one thing and grateful for another, and an apology does not silently erase a betrayal.
 
+This however is something that I haven't implementing or plan to implement anytime soon. The mathematical models described in NLAVS is still very abstract and subject to a lot of changes. CAA and RepE is still cutting edge research that I'm still reading papers about.
+
+Omnia might get an affect vector system however, it's going to be more simplistic than what the NLAVS proposal scribbles down.
+
 ## A Research Instrument: Model Psychology in Fiction
 
-Omnia's architecture doubles as an apparatus for studying how language models behave _as characters_ under controlled epistemic conditions — something uni-agent setups cannot do, because they can neither control what the model knows nor observe what it withholds.
+Omnia's architecture doubles as an apparatus for studying how language models behave _as characters_ under controlled epistemic conditions.
 
-- **A window into private reasoning.** Monologue intents are the model's in-character thoughts: unperceived by other agents, exempt from validation, but durably logged. You can directly compare what a character _thinks_ against what it _says and does_ — measuring deception, self-consistency, motivated reasoning, or the gap between private appraisal and public behavior.
-- **Knowledge as an experimental variable.** Attribute ACLs let you administer information with precision: give one agent a fact, withhold it from another, and observe propagation, inference, and leakage through dialogue alone. Secret-keeping stops being anecdotal and becomes testable — _provably_, since the engine logs exactly what each agent was ever shown.
-- **Controlled, reproducible conditions.** A scenario is a JSON file; a run is a SQLite database. Identical initial conditions, swappable model providers behind one interface (`ILLMProvider`), and a deterministic mock for baselines. Rerun the white-room experiment a hundred times, vary one attribute, and diff the transcripts.
-- **Multi-agent social dynamics with ground truth.** Because objective world state exists independently of any agent's beliefs, you can score agents' beliefs and claims against reality — hallucination, confabulation, and social conformity become measurable quantities rather than impressions.
+- **A window into private reasoning.** Monologue intents are the model's in character thoughts: unperceived by other agents, exempt from validation, but durably logged. You can directly compare what a character _thinks_ against what it _says and does_: measuring deception, self-consistency, motivated reasoning, etc.
+- **Knowledge as an experimental variable.** Attribute ACLs let you administer information with precision: give one agent a fact, withhold it from another, and observe propagation, inference, and leakage through dialogue alone.
+- **Controlled, reproducible conditions.** A scenario is a JSON file (like a template); a run is a SQLite database. Identical initial conditions, swappable model providers behind one interface (`ILLMProvider`), and a deterministic mock for baselines. Rerun the scenario a hundred times, vary one attribute, and diff the transcripts.
+- **Multi agent social dynamics with ground truth.** Because objective world state exists independently of any agent's beliefs, you can score agents' beliefs and claims against reality like hallucination. Even social conformity become measurable quantities rather than impressions or _✨ vibes_.
 
-The bundled demo scenario is exactly this: [`talking-room`](./content/demo/scenarios/talking-room.json) places two memory-wiped subjects in a featureless white room — each knowing their own name but not the other's — and observes what they do. It runs today, via the CLI, with a human optionally playing either subject.
+The bundled demo scenario is exactly this: [`talking-room`](./content/demo/scenarios/talking-room.json) places two memory wiped subjects in a featureless white room. Each know their own name but not the other's. Observe what they do. It runs today, ~~via the CLI, with a human optionally playing either subject~~ via a GUI which is in rapid development. You can let it run forever autonomously or roleplay as either character.
 
 ## Project Status: What `v0` Means
 
@@ -112,15 +164,15 @@ The finish line for the first milestone is small on purpose.
 
 - [x] Two hand-authored NPCs live in one location, playable via CLI.
 - [ ] Each has buffer and vector-archive memory and recalls something said a few turns earlier. _(buffer: done; vector archive: not started)_
-- [ ] One NPC knows a fact the other does not and, provably by testing, will not leak it.
+- [x] One NPC knows a fact the other does not and, provably by testing, will not leak it.
 - [x] The Architect processes at least one non-trivial action per exchange with a visible state change.
 - [x] The whole thing persists to a SQLite file and reloads identically.
 
-**Explicitly out of scope for `v0`:** Constraint validators (beyond basic sense-checking), multi-location perception, affect-vector decay math, the Dossier, whims/simulation tiering, the delta ledger, and UI beyond CLI.
+**Explicitly out of scope for `v0`:** Constraint validators (beyond basic sense-checking), multi-location perception, affect-vector decay math, the Dossier, whims/simulation tiering, the delta ledger.
 
 ### A Note on Tech Debt
 
-The Architect currently trusts an LLM's judgement about reasonable consequences rather than validating every change against declarative constraints. A general constraint solver is worth building eventually, but building it before anything is playable is foundational perfectionism that produces beautiful architecture and no game. `v0` keeps the single-call Architect on purpose.
+The Architect currently trusts an LLM's judgement about reasonable consequences rather than validating every change against declarative constraints. A general constraint solver is worth building eventually, but building it before anything is playable is foundational perfectionism that produces beautiful architecture and no framework. `v0` keeps the single-call Architect on purpose.
 
 ## Repository Layout
 
@@ -138,17 +190,16 @@ omnia/
     llm/         ILLMProvider interface plus Gemini and deterministic mock implementations
     scenario/    scenario JSON schema and loader (JSON → SQLite)
   apps/
-    cli/         the playable loop (human or LLM actors, --scenario / --play flags)
+    gui/         Next.js Web GUI dashboard and simulation runner
   content/
     demo/              bundled scenarios (talking-room)
   tests/
     integration/ cross-package tests against a mocked LLM
     evals/       deliberate real-API evaluation runs
-  docs/          Astro documentation site (→ web/docs/)
+  web/
+    docs/        Astro documentation site
 ```
 
-_The engine core deliberately knows nothing about domain content (stats, traits, genres). Scenarios are plain JSON the loader ingests; what an attribute means is the scenario's business, not the engine's._
-
 ## Roadmap (Build Order after `v0`)
 
 1. Vector-archive memory and retrieval (closing out the `v0` memory milestone).

apps/gui/next-env.d.ts

@@ -1,6 +1,6 @@
 /// <reference types="next" />
 /// <reference types="next/image-types/global" />
-import "./.next/types/routes.d.ts";
+import "./.next/dev/types/routes.d.ts";
 
 // NOTE: This file should not be edited
 // see https://nextjs.org/docs/app/api-reference/config/typescript for more information.

apps/gui/package.json

@@ -10,14 +10,14 @@
     "lint": "next lint"
   },
   "dependencies": {
-    "@omnia/core": "workspace:*",
-    "@omnia/llm": "workspace:*",
-    "@omnia/intent": "workspace:*",
-    "@omnia/architect": "workspace:*",
     "@omnia/actor": "workspace:*",
+    "@omnia/architect": "workspace:*",
+    "@omnia/core": "workspace:*",
+    "@omnia/intent": "workspace:*",
+    "@omnia/llm": "workspace:*",
     "@omnia/memory": "workspace:*",
-    "@omnia/spatial": "workspace:*",
     "@omnia/scenario": "workspace:*",
+    "@omnia/spatial": "workspace:*",
     "dotenv": "^17.4.2",
     "next": "^16.2.10",
     "react": "^19.2.0",
@@ -27,6 +27,9 @@
     "@types/node": "^26.1.0",
     "@types/react": "^19.2.0",
     "@types/react-dom": "^19.2.0",
+    "autoprefixer": "^10.5.2",
+    "postcss": "^8.5.16",
+    "tailwindcss": "^3.4.19",
     "typescript": "^6.0.3"
   }
 }

apps/gui/postcss.config.mjs

@@ -0,0 +1,8 @@
+const config = {
+  plugins: {
+    tailwindcss: {},
+    autoprefixer: {},
+  },
+};
+
+export default config;

apps/gui/src/app/config/page.tsx

@@ -10,8 +10,10 @@ import {
   getProviderMappings,
   setProviderMapping,
   updateProviderInstance,
+  getAvailableProviders,
+  regenerateEmbeddings,
 } from "@/app/play/actions";
-import type { LLMProviderInstance } from "@omnia/llm";
+import type { ModelProviderInstance, ModelProviderMeta } from "@omnia/llm";
 
 interface ConfigStatus {
   apiKeySet: boolean;
@@ -22,8 +24,9 @@ interface ConfigStatus {
 
 export default function ConfigPage() {
   const [config, setConfig] = useState<ConfigStatus | null>(null);
-  const [instances, setInstances] = useState<LLMProviderInstance[]>([]);
+  const [instances, setInstances] = useState<ModelProviderInstance[]>([]);
   const [mappings, setMappings] = useState<Record<string, string>>({});
+  const [availableProviders, setAvailableProviders] = useState<ModelProviderMeta[]>([]);
   const [loading, setLoading] = useState(true);
   const [error, setError] = useState("");
 
@@ -33,13 +36,17 @@ export default function ConfigPage() {
   const [editKey, setEditKey] = useState("");
   const [editModel, setEditModel] = useState("gemini-2.5-flash");
   const [editIsActive, setEditIsActive] = useState(false);
+  const [editType, setEditType] = useState<"generative" | "embedding">("generative");
 
   useEffect(() => {
     if (selectedInstanceId === "new") {
       setEditName("");
-      setEditProvider("google-genai");
+      const defaultProvider = "google-genai";
+      setEditProvider(defaultProvider);
       setEditKey("");
-      setEditModel("gemini-2.5-flash");
+      setEditType("generative");
+      const pMeta = availableProviders.find((p) => p.id === defaultProvider);
+      setEditModel(pMeta?.defaultModel || "gemini-2.5-flash");
       setEditIsActive(false);
     } else {
       const inst = instances.find((i) => i.id === selectedInstanceId);
@@ -47,11 +54,29 @@ export default function ConfigPage() {
         setEditName(inst.name);
         setEditProvider(inst.providerName);
         setEditKey("");
-        setEditModel(inst.modelName || "gemini-2.5-flash");
+        setEditType(inst.type || "generative");
+        const pMeta = availableProviders.find((p) => p.id === inst.providerName);
+        setEditModel(inst.modelName || (inst.type === "embedding" ? pMeta?.defaultEmbeddingModel : pMeta?.defaultModel) || "gemini-2.5-flash");
         setEditIsActive(inst.isActive);
       }
     }
-  }, [selectedInstanceId, instances]);
+  }, [selectedInstanceId, instances, availableProviders]);
+
+  const handleProviderChange = (providerId: string) => {
+    setEditProvider(providerId);
+    const pMeta = availableProviders.find((p) => p.id === providerId);
+    if (pMeta) {
+      setEditModel(editType === "embedding" ? pMeta.defaultEmbeddingModel : pMeta.defaultModel);
+    }
+  };
+
+  const handleTypeChange = (type: "generative" | "embedding") => {
+    setEditType(type);
+    const pMeta = availableProviders.find((p) => p.id === editProvider);
+    if (pMeta) {
+      setEditModel(type === "embedding" ? pMeta.defaultEmbeddingModel : pMeta.defaultModel);
+    }
+  };
 
   const loadInstances = useCallback(async () => {
     try {
@@ -79,6 +104,8 @@ export default function ConfigPage() {
       setConfig(result);
       await loadInstances();
       await loadMappings();
+      const provs = await getAvailableProviders();
+      setAvailableProviders(provs);
     } catch (err) {
       setError(err instanceof Error ? err.message : String(err));
     } finally {
@@ -101,19 +128,42 @@ export default function ConfigPage() {
       setLoading(true);
       setError("");
 
+      let shouldRegenerate = false;
+      let targetInstanceId = selectedInstanceId;
+
       if (selectedInstanceId === "new") {
         if (!editKey.trim()) {
           setError("API Key is required for new instances.");
           setLoading(false);
           return;
         }
-        const created = await createProviderInstance(editName, editProvider, editKey, editModel || undefined);
+        const created = await createProviderInstance(editName, editProvider, editKey, editModel || undefined, editType);
         if (editIsActive) {
           await setActiveProviderInstance(created.id);
         }
+        targetInstanceId = created.id;
         setSelectedInstanceId(created.id);
       } else {
-        await updateProviderInstance(selectedInstanceId, editName, editProvider, editKey || undefined, editModel || undefined);
+        const inst = instances.find((i) => i.id === selectedInstanceId);
+        if (inst && inst.type === "embedding") {
+          const isMapped = mappings["embeddings"] === selectedInstanceId;
+          const isActive = inst.isActive && !mappings["embeddings"];
+          if (isMapped || isActive) {
+            const hasChanged = inst.providerName !== editProvider || inst.modelName !== editModel;
+            if (hasChanged) {
+              const confirmChange = window.confirm(
+                "You have changed the configuration of the active embedding provider. This will delete all existing embeddings and regenerate them from scratch. Are you sure you want to do this?"
+              );
+              if (!confirmChange) {
+                setLoading(false);
+                return;
+              }
+              shouldRegenerate = true;
+            }
+          }
+        }
+
+        await updateProviderInstance(selectedInstanceId, editName, editProvider, editKey || undefined, editModel || undefined, editType);
         if (editIsActive) {
           await setActiveProviderInstance(selectedInstanceId);
         }
@@ -121,6 +171,10 @@ export default function ConfigPage() {
 
       await loadInstances();
       await loadMappings();
+
+      if (shouldRegenerate && targetInstanceId !== "new") {
+        await regenerateEmbeddings(targetInstanceId);
+      }
     } catch (err) {
       setError(err instanceof Error ? err.message : String(err));
     } finally {
@@ -147,9 +201,19 @@ export default function ConfigPage() {
   };
 
   const handleUpdateMapping = async (task: string, providerInstanceId: string) => {
+    if (task === "embeddings" && mappings[task] !== providerInstanceId) {
+      const confirmChange = window.confirm(
+        "Changing the embeddings provider will delete all existing embeddings and regenerate them from scratch. Are you sure you want to do this?"
+      );
+      if (!confirmChange) return;
+    }
+
     try {
       setLoading(true);
       await setProviderMapping(task, providerInstanceId);
+      if (task === "embeddings") {
+        await regenerateEmbeddings(providerInstanceId);
+      }
       await loadMappings();
     } catch (err) {
       setError(err instanceof Error ? err.message : String(err));
@@ -159,44 +223,57 @@ export default function ConfigPage() {
   };
 
   return (
-    <div className="config-page">
-      <h1>Configuration</h1>
+    <div className="mx-auto max-w-[800px] px-4 py-8">
+      <h1 className="mb-6 text-2xl">Configuration</h1>
 
       {loading && <p>Loading configuration...</p>}
-      {error && <div className="error-banner">{error}</div>}
+      {error && (
+        <div className="mb-4 rounded border border-red-300 bg-red-50 px-3 py-2 text-sm text-red-700">
+          {error}
+        </div>
+      )}
 
       {config && !loading && (
         <>
-          <section className="config-section">
-            <h2>LLM Provider Instances</h2>
-            <div className="provider-split-container">
-              
+          <section className="mb-8 border-b border-gray-200 pb-6">
+            <h2 className="mb-3 text-lg">LLM Provider Instances</h2>
+            <div className="mt-4 grid min-h-[400px] grid-cols-1 overflow-hidden rounded-xl border border-gray-200 bg-white md:grid-cols-[30%_70%]">
               {/* 30% area */}
-              <div className="provider-list-pane">
-                <div className="pane-header">
-                  <h3>Instances</h3>
+              <div className="flex flex-col border-r border-gray-200 bg-gray-50">
+                <div className="flex items-center justify-between border-b border-gray-200 bg-gray-100 px-4 py-4">
+                  <h3 className="m-0 text-[0.95rem] font-semibold text-[#111]">Instances</h3>
                   <button
                     onClick={() => setSelectedInstanceId("new")}
-                    className="btn-add-inst"
+                    className="cursor-pointer rounded-md bg-emerald-500 px-3 py-1.5 text-xs font-medium text-white transition-colors hover:bg-emerald-600"
                     type="button"
                   >
                     + Add
                   </button>
                 </div>
-                <div className="pane-list">
+                <div className="flex flex-1 flex-col overflow-y-auto">
                   {instances.length === 0 ? (
-                    <div className="no-instances-msg">No instances configured</div>
+                    <div className="px-4 py-8 text-center text-xs text-gray-400">
+                      No instances configured
+                    </div>
                   ) : (
                     instances.map((inst) => (
                       <div
                         key={inst.id}
                         onClick={() => setSelectedInstanceId(inst.id)}
-                        className={`instance-list-item ${selectedInstanceId === inst.id ? "active" : ""}`}
+                        className={`cursor-pointer border-b border-gray-200 border-l-[3px] px-4 py-4 transition-all hover:bg-gray-100 ${
+                          selectedInstanceId === inst.id
+                            ? "border-l-blue-500 bg-blue-50"
+                            : "border-l-transparent"
+                        }`}
                       >
-                        <div className="item-name">{inst.name}</div>
-                        <div className="item-meta">
-                          <span>{inst.providerName}</span>
-                          {inst.isActive && <span className="active-pill">Active</span>}
+                        <div className="text-sm font-medium text-[#111]">{inst.name}</div>
+                        <div className="mt-1 flex items-center justify-between text-xs text-gray-500">
+                          <span>{inst.providerName} ({inst.type || "generative"})</span>
+                          {inst.isActive && (
+                            <span className="rounded-full bg-green-100 px-1.5 py-[1px] text-[0.65rem] font-semibold text-green-700">
+                              Active
+                            </span>
+                          )}
                         </div>
                       </div>
                     ))
@@ -205,17 +282,19 @@ export default function ConfigPage() {
               </div>
 
               {/* 70% area */}
-              <div className="provider-form-pane">
-                <form onSubmit={handleSave} className="provider-config-form">
-                  <div className="form-scroll-content">
-                    <h3>
+              <div className="flex flex-col bg-white">
+                <form onSubmit={handleSave} className="flex h-full flex-col justify-between">
+                  <div className="flex flex-1 flex-col gap-5 p-6">
+                    <h3 className="m-0 mb-2 text-lg font-semibold text-[#111]">
                       {selectedInstanceId === "new"
                         ? "Create New Provider Instance"
                         : `Configure: ${editName}`}
                     </h3>
 
-                    <div className="form-group">
-                      <label htmlFor="formName">Friendly Name</label>
+                    <div className="flex flex-col gap-1.5">
+                      <label htmlFor="formName" className="text-xs font-medium text-gray-700">
+                        Friendly Name
+                      </label>
                       <input
                         id="formName"
                         type="text"
@@ -223,23 +302,52 @@ export default function ConfigPage() {
                         onChange={(e) => setEditName(e.target.value)}
                         placeholder="e.g. Gemini - Production"
                         required
+                        className="w-full rounded-md border border-gray-300 bg-white px-3 py-2 text-sm outline-none transition-[border-color,box-shadow] focus:border-blue-500 focus:ring-3 focus:ring-blue-500/15"
                       />
                     </div>
 
-                    <div className="form-group">
-                      <label htmlFor="formProvider">Provider Type</label>
+                    <div className="flex flex-col gap-1.5">
+                      <label htmlFor="formType" className="text-xs font-medium text-gray-700">
+                        Instance Type
+                      </label>
                       <select
-                        id="formProvider"
-                        value={editProvider}
-                        onChange={(e) => setEditProvider(e.target.value)}
+                        id="formType"
+                        value={editType}
+                        onChange={(e) => handleTypeChange(e.target.value as "generative" | "embedding")}
+                        className="w-full rounded-md border border-gray-300 bg-white px-3 py-2 text-sm outline-none transition-[border-color,box-shadow] focus:border-blue-500 focus:ring-3 focus:ring-blue-500/15"
                       >
-                        <option value="google-genai">Google Gemini (Gemini-2.5-flash)</option>
-                        <option value="mock">Mock LLM Provider</option>
+                        <option value="generative">Generative (Chat / Text Completion)</option>
+                        <option value="embedding">Embedding (Vector generation)</option>
                       </select>
                     </div>
 
-                    <div className="form-group">
-                      <label htmlFor="formKey">API Key</label>
+                    <div className="flex flex-col gap-1.5">
+                      <label htmlFor="formProvider" className="text-xs font-medium text-gray-700">
+                        Provider Type
+                      </label>
+                      <select
+                        id="formProvider"
+                        value={editProvider}
+                        onChange={(e) => handleProviderChange(e.target.value)}
+                        className="w-full rounded-md border border-gray-300 bg-white px-3 py-2 text-sm outline-none transition-[border-color,box-shadow] focus:border-blue-500 focus:ring-3 focus:ring-blue-500/15"
+                      >
+                        {availableProviders.map((p) => (
+                          <option key={p.id} value={p.id}>
+                            {p.displayName}
+                          </option>
+                        ))}
+                      </select>
+                      {editProvider && availableProviders.length > 0 && (
+                        <span className="mt-1 block rounded border border-gray-200 bg-gray-100 px-3 py-2 text-xs text-gray-600">
+                          {availableProviders.find((p) => p.id === editProvider)?.description}
+                        </span>
+                      )}
+                    </div>
+
+                    <div className="flex flex-col gap-1.5">
+                      <label htmlFor="formKey" className="text-xs font-medium text-gray-700">
+                        API Key
+                      </label>
                       <input
                         id="formKey"
                         type="password"
@@ -251,104 +359,123 @@ export default function ConfigPage() {
                             : "•••••••• (unchanged)"
                         }
                         required={selectedInstanceId === "new"}
+                        className="w-full rounded-md border border-gray-300 bg-white px-3 py-2 text-sm outline-none transition-[border-color,box-shadow] focus:border-blue-500 focus:ring-3 focus:ring-blue-500/15"
                       />
                     </div>
 
-                    <div className="form-group">
-                      <label htmlFor="formModel">Model Name</label>
+                    <div className="flex flex-col gap-1.5">
+                      <label htmlFor="formModel" className="text-xs font-medium text-gray-700">
+                        Model Name
+                      </label>
                       <input
                         id="formModel"
                         type="text"
                         value={editModel}
                         onChange={(e) => setEditModel(e.target.value)}
                         placeholder="e.g. gemini-2.5-flash, gemini-2.5-pro"
+                        className="w-full rounded-md border border-gray-300 bg-white px-3 py-2 text-sm outline-none transition-[border-color,box-shadow] focus:border-blue-500 focus:ring-3 focus:ring-blue-500/15"
                       />
                     </div>
 
-                    <div className="form-group checkbox-group">
+                    <div className="mt-1 flex flex-row items-center gap-2">
                       <input
                         id="formActive"
                         type="checkbox"
                         checked={editIsActive}
                         onChange={(e) => setEditIsActive(e.target.checked)}
+                        className="h-4 w-4 cursor-pointer"
                       />
-                      <label htmlFor="formActive">Set as Active Instance</label>
+                      <label htmlFor="formActive" className="cursor-pointer text-xs font-medium text-gray-700">
+                        Set as Active Instance
+                      </label>
                     </div>
                   </div>
 
-                  <div className="form-actions-bar">
-                    <div className="action-left">
+                  <div className="flex items-center justify-between border-t border-gray-200 bg-gray-50 px-6 py-4">
+                    <div>
                       {selectedInstanceId !== "new" && (
                         <button
                           type="button"
                           onClick={handleDelete}
                           disabled={loading}
-                          className="btn-delete-pane"
+                          className="cursor-pointer rounded-md bg-red-500 px-4 py-2 text-sm font-medium text-white transition-colors hover:bg-red-600 disabled:opacity-50"
                         >
                           Delete
                         </button>
                       )}
                     </div>
-                    <div className="action-right">
-                      <button type="submit" disabled={loading} className="btn-save-pane">
+                    <div>
+                      <button
+                        type="submit"
+                        disabled={loading}
+                        className="cursor-pointer rounded-md bg-blue-600 px-5 py-2 text-sm font-medium text-white transition-colors hover:bg-blue-700 disabled:opacity-50"
+                      >
                         {loading ? "Saving..." : "Save"}
                       </button>
                     </div>
                   </div>
                 </form>
               </div>
-
             </div>
           </section>
 
-          <section className="config-section">
-            <h2>Task Provider Routing</h2>
-            <p className="config-hint" style={{ background: "#eff6ff", border: "1px solid #bfdbfe", color: "#1e3a8a", margin: "1rem 0" }}>
-              Configure which LLM Provider Key Instance should handle each specific simulation task. Mappings default to the currently <strong>Active</strong> instance if not specified.
+          <section className="mb-8 border-b border-gray-200 pb-6">
+            <h2 className="mb-3 text-lg">Task Provider Routing</h2>
+            <p className="my-4 rounded border border-blue-200 bg-blue-50 px-3 py-2 text-xs text-blue-800">
+              Configure which LLM Provider Key Instance should handle each specific simulation
+              task. Mappings default to the currently <strong>Active</strong> instance if not
+              specified.
             </p>
-            <div className="mappings-grid">
+            <div className="mt-4 grid grid-cols-1 gap-4 md:grid-cols-2">
               {[
-                { key: "actor-prose", label: "Actor Prose Generation", desc: "Generates roleplay/narrative prose for Non-Player Characters." },
-                { key: "llm-validator", label: "LLM Validator", desc: "Arbitrates and validates proposed actions against the world state rules." },
-                { key: "intent-decoder", label: "Intent Decoder", desc: "Splits raw prose actions into structured intents (Player and NPC)." },
-                { key: "timedelta", label: "TimeDelta Generator", desc: "Calculates the duration of character actions to advance the game clock." },
+                { key: "actor-prose", label: "Actor Prose Generation", desc: "Generates roleplay/narrative prose for Non-Player Characters.", type: "generative" },
+                { key: "llm-validator", label: "LLM Validator", desc: "Arbitrates and validates proposed actions against the world state rules.", type: "generative" },
+                { key: "intent-decoder", label: "Intent Decoder", desc: "Splits raw prose actions into structured intents (Player and NPC).", type: "generative" },
+                { key: "timedelta", label: "TimeDelta Generator", desc: "Calculates the duration of character actions to advance the game clock.", type: "generative" },
+                { key: "embeddings", label: "Text Embeddings Generator", desc: "Generates vector embeddings for long-term memory retrieval.", type: "embedding" },
               ].map((task) => (
-                <div key={task.key} className="mapping-card">
-                  <div className="mapping-info">
-                    <strong>{task.label}</strong>
-                    <span className="text-gray" style={{ fontSize: "0.75rem", marginTop: "0.125rem" }}>{task.desc}</span>
+                <div
+                  key={task.key}
+                  className="flex flex-col justify-between gap-3 rounded-lg border border-gray-200 bg-gray-50 p-4"
+                >
+                  <div className="flex flex-col gap-1 text-xs">
+                    <strong className="text-sm text-[#111]">{task.label}</strong>
+                    <span className="mt-0.5 text-gray-500">{task.desc}</span>
                   </div>
                   <select
                     value={mappings[task.key] || ""}
                     onChange={(e) => handleUpdateMapping(task.key, e.target.value)}
+                    className="w-full rounded border border-gray-300 bg-white px-2 py-1.5 text-xs"
                   >
                     <option value="">-- Use Active Key (Default) --</option>
-                    {instances.map((inst) => (
-                      <option key={inst.id} value={inst.id}>
-                        {inst.name} ({inst.providerName}){inst.isActive ? " [Active]" : ""}
-                      </option>
-                    ))}
+                    {instances
+                      .filter((inst) => (inst.type || "generative") === task.type)
+                      .map((inst) => (
+                        <option key={inst.id} value={inst.id}>
+                          {inst.name} ({inst.providerName}){inst.isActive ? " [Active]" : ""}
+                        </option>
+                      ))}
                   </select>
                 </div>
               ))}
             </div>
           </section>
 
-          <section className="config-section">
-            <h2>Environment Variables Default</h2>
-            <div className="config-row">
-              <span className="config-label">Default Model</span>
-              <span className="config-value">
-                <code>{config.model}</code>
+          <section className="mb-8 border-b border-gray-200 pb-6">
+            <h2 className="mb-3 text-lg">Environment Variables Default</h2>
+            <div className="flex justify-between border-b border-gray-100 py-1.5">
+              <span className="text-sm text-gray-500">Default Model</span>
+              <span className="text-sm">
+                <code className="font-mono text-sm">{config.model}</code>
               </span>
             </div>
-            <div className="config-row">
-              <span className="config-label">Default API Key (.env)</span>
+            <div className="flex justify-between border-b border-gray-100 py-1.5">
+              <span className="text-sm text-gray-500">Default API Key (.env)</span>
               <span
                 className={
                   config.apiKeySet
-                    ? "config-value status-ok"
-                    : "config-value status-error"
+                    ? "text-sm text-green-600"
+                    : "text-sm font-medium text-red-600"
                 }
               >
                 {config.apiKeySet
@@ -358,26 +485,30 @@ export default function ConfigPage() {
             </div>
           </section>
 
-          <section className="config-section">
-            <h2>Available Scenarios</h2>
+          <section className="mb-8 border-b border-gray-200 pb-6">
+            <h2 className="mb-3 text-lg">Available Scenarios</h2>
             {config.availableScenarios.length === 0 ? (
-              <p className="config-hint">
-                No scenarios found in <code>content/demo/scenarios/</code>.
+              <p className="mt-3 rounded border border-amber-200 bg-amber-100 px-3 py-2 text-xs text-amber-800">
+                No scenarios found in <code className="font-mono text-xs">content/demo/scenarios/</code>.
               </p>
             ) : (
-              <table className="scenario-table">
+              <table className="w-full border-collapse text-sm">
                 <thead>
                   <tr>
-                    <th>Name</th>
-                    <th>Path</th>
+                    <th className="border-b-2 border-gray-200 p-2 text-left font-medium text-gray-500">
+                      Name
+                    </th>
+                    <th className="border-b-2 border-gray-200 p-2 text-left font-medium text-gray-500">
+                      Path
+                    </th>
                   </tr>
                 </thead>
                 <tbody>
                   {config.availableScenarios.map((s) => (
                     <tr key={s.path}>
-                      <td>{s.name}</td>
-                      <td>
-                        <code>{s.path}</code>
+                      <td className="border-b border-gray-100 p-2">{s.name}</td>
+                      <td className="border-b border-gray-100 p-2">
+                        <code className="font-mono text-xs text-blue-600">{s.path}</code>
                       </td>
                     </tr>
                   ))}
@@ -386,392 +517,18 @@ export default function ConfigPage() {
             )}
           </section>
 
-          <section className="config-section">
-            <h2>Engine Packages</h2>
-            <p className="config-hint">
-              All <code>@omnia/*</code> workspace packages are consumed via{" "}
-              <code>transpilePackages</code> in <code>next.config.ts</code>.
-              The native <code>better-sqlite3</code> module is externalized via{" "}
-              <code>serverExternalPackages</code>.
+          <section className="mb-8 border-b border-gray-200 pb-6">
+            <h2 className="mb-3 text-lg">Engine Packages</h2>
+            <p className="mt-3 rounded border border-amber-200 bg-amber-100 px-3 py-2 text-xs text-amber-800">
+              All <code className="font-mono text-xs">@omnia/*</code> workspace packages are
+              consumed via <code className="font-mono text-xs">transpilePackages</code> in{" "}
+              <code className="font-mono text-xs">next.config.ts</code>. The native{" "}
+              <code className="font-mono text-xs">better-sqlite3</code> module is externalized
+              via <code className="font-mono text-xs">serverExternalPackages</code>.
             </p>
           </section>
         </>
       )}
-
-      <style>{`
-        .config-page {
-          max-width: 800px;
-          margin: 0 auto;
-          padding: 2rem 1rem;
-        }
-        .config-page h1 {
-          font-size: 1.5rem;
-          margin-bottom: 1.5rem;
-        }
-        .config-section {
-          margin-bottom: 2rem;
-          padding-bottom: 1.5rem;
-          border-bottom: 1px solid #e5e7eb;
-        }
-        .config-section h2 {
-          font-size: 1.125rem;
-          margin-bottom: 0.75rem;
-        }
-        .config-row {
-          display: flex;
-          justify-content: space-between;
-          padding: 0.375rem 0;
-          border-bottom: 1px solid #f3f4f6;
-        }
-        .config-label {
-          color: #555;
-          font-size: 0.875rem;
-        }
-        .config-value {
-          font-size: 0.875rem;
-        }
-        .status-ok {
-          color: #16a34a;
-        }
-        .status-error {
-          color: #dc2626;
-          font-weight: 500;
-        }
-        .config-hint {
-          margin-top: 0.75rem;
-          padding: 0.5rem 0.75rem;
-          background: #fef3c7;
-          border: 1px solid #fde68a;
-          border-radius: 4px;
-          font-size: 0.8125rem;
-          color: #92400e;
-        }
-        .config-hint code {
-          background: rgba(0,0,0,0.06);
-          padding: 0.125rem 0.25rem;
-          border-radius: 2px;
-          font-size: 0.75rem;
-        }
-        .error-banner {
-          background: #fef2f2;
-          color: #b91c1c;
-          border: 1px solid #fca5a5;
-          border-radius: 4px;
-          padding: 0.5rem 0.75rem;
-          font-size: 0.875rem;
-          margin-bottom: 1rem;
-        }
-        .scenario-table {
-          width: 100%;
-          border-collapse: collapse;
-          font-size: 0.875rem;
-        }
-        .scenario-table th {
-          text-align: left;
-          padding: 0.5rem;
-          border-bottom: 2px solid #e5e7eb;
-          color: #555;
-          font-weight: 500;
-        }
-        .scenario-table td {
-          padding: 0.5rem;
-          border-bottom: 1px solid #f3f4f6;
-        }
-        .scenario-table code {
-          font-size: 0.8125rem;
-          color: #2563eb;
-        }
-        code {
-          font-family: monospace;
-          font-size: 0.875rem;
-        }
-
-        /* Pill and List Styles */
-        .status-pill {
-          display: inline-block;
-          padding: 0.125rem 0.5rem;
-          border-radius: 9999px;
-          font-size: 0.75rem;
-          font-weight: 600;
-        }
-        .status-pill.active {
-          background: #dcfce7;
-          color: #15803d;
-        }
-        .status-pill.inactive {
-          background: #f3f4f6;
-          color: #4b5563;
-        }
-        .action-buttons {
-          display: flex;
-          gap: 0.5rem;
-          align-items: center;
-        }
-        .btn-sm {
-          padding: 0.25rem 0.5rem;
-          font-size: 0.75rem;
-          background: #3b82f6;
-          color: #fff;
-          border: none;
-          border-radius: 4px;
-          cursor: pointer;
-        }
-        .btn-sm:hover {
-          background: #2563eb;
-        }
-        .btn-sm.delete-btn {
-          background: #ef4444;
-        }
-        .btn-sm.delete-btn:hover {
-          background: #dc2626;
-        }
-        /* Split container */
-        .provider-split-container {
-          display: grid;
-          grid-template-columns: 1fr;
-          border: 1px solid #e5e7eb;
-          border-radius: 12px;
-          overflow: hidden;
-          background: #fff;
-          margin-top: 1rem;
-          min-height: 400px;
-        }
-        @media (min-width: 768px) {
-          .provider-split-container {
-            grid-template-columns: 30% 70%;
-          }
-        }
-
-        /* 30% List Pane */
-        .provider-list-pane {
-          border-right: 1px solid #e5e7eb;
-          background: #f9fafb;
-          display: flex;
-          flex-direction: column;
-        }
-        .pane-header {
-          display: flex;
-          justify-content: space-between;
-          align-items: center;
-          padding: 1rem;
-          border-bottom: 1px solid #e5e7eb;
-          background: #f3f4f6;
-        }
-        .pane-header h3 {
-          margin: 0;
-          font-size: 0.95rem;
-          font-weight: 600;
-          color: #111;
-        }
-        .btn-add-inst {
-          padding: 0.375rem 0.75rem;
-          font-size: 0.8125rem;
-          font-weight: 500;
-          background: #10b981;
-          color: #fff;
-          border: none;
-          border-radius: 6px;
-          cursor: pointer;
-          transition: background 0.2s;
-        }
-        .btn-add-inst:hover {
-          background: #059669;
-        }
-        .pane-list {
-          overflow-y: auto;
-          flex: 1;
-          display: flex;
-          flex-direction: column;
-        }
-        .no-instances-msg {
-          padding: 2rem 1rem;
-          text-align: center;
-          color: #6b7280;
-          font-size: 0.8125rem;
-        }
-        .instance-list-item {
-          padding: 1rem;
-          border-bottom: 1px solid #e5e7eb;
-          cursor: pointer;
-          transition: background 0.15s, border-left 0.15s;
-          border-left: 3px solid transparent;
-        }
-        .instance-list-item:hover {
-          background: #f3f4f6;
-        }
-        .instance-list-item.active {
-          background: #eff6ff;
-          border-left: 3px solid #3b82f6;
-        }
-        .item-name {
-          font-weight: 500;
-          font-size: 0.875rem;
-          color: #111;
-        }
-        .item-meta {
-          display: flex;
-          justify-content: space-between;
-          align-items: center;
-          margin-top: 0.25rem;
-          font-size: 0.75rem;
-          color: #6b7280;
-        }
-        .active-pill {
-          background: #dcfce7;
-          color: #15803d;
-          font-weight: 600;
-          padding: 0.0625rem 0.375rem;
-          border-radius: 9999px;
-        }
-
-        /* 70% Form Pane */
-        .provider-form-pane {
-          background: #fff;
-          display: flex;
-          flex-direction: column;
-        }
-        .provider-config-form {
-          display: flex;
-          flex-direction: column;
-          height: 100%;
-          justify-content: space-between;
-        }
-        .form-scroll-content {
-          padding: 1.5rem;
-          flex: 1;
-          display: flex;
-          flex-direction: column;
-          gap: 1.25rem;
-        }
-        .form-scroll-content h3 {
-          margin: 0 0 0.5rem 0;
-          font-size: 1.125rem;
-          font-weight: 600;
-          color: #111;
-        }
-        .form-group {
-          display: flex;
-          flex-direction: column;
-          gap: 0.375rem;
-        }
-        .form-group label {
-          font-size: 0.8125rem;
-          font-weight: 500;
-          color: #374151;
-        }
-        .form-group input[type="text"],
-        .form-group input[type="password"],
-        .form-group select {
-          padding: 0.5rem 0.75rem;
-          font-size: 0.875rem;
-          border: 1px solid #d1d5db;
-          border-radius: 6px;
-          background: #fff;
-          outline: none;
-          transition: border-color 0.15s, box-shadow 0.15s;
-        }
-        .form-group input:focus,
-        .form-group select:focus {
-          border-color: #3b82f6;
-          box-shadow: 0 0 0 3px rgba(59, 130, 246, 0.15);
-        }
-        .checkbox-group {
-          flex-direction: row;
-          align-items: center;
-          gap: 0.5rem;
-          margin-top: 0.25rem;
-        }
-        .checkbox-group label {
-          cursor: pointer;
-        }
-        .checkbox-group input {
-          width: 1rem;
-          height: 1rem;
-          cursor: pointer;
-        }
-
-        /* Action bar */
-        .form-actions-bar {
-          padding: 1rem 1.5rem;
-          border-top: 1px solid #e5e7eb;
-          background: #f9fafb;
-          display: flex;
-          justify-content: space-between;
-          align-items: center;
-        }
-        .btn-delete-pane {
-          padding: 0.5rem 1rem;
-          font-size: 0.875rem;
-          font-weight: 500;
-          background: #ef4444;
-          color: #fff;
-          border: none;
-          border-radius: 6px;
-          cursor: pointer;
-          transition: background 0.2s;
-        }
-        .btn-delete-pane:hover {
-          background: #dc2626;
-        }
-        .btn-save-pane {
-          padding: 0.5rem 1.25rem;
-          font-size: 0.875rem;
-          font-weight: 500;
-          background: #2563eb;
-          color: #fff;
-          border: none;
-          border-radius: 6px;
-          cursor: pointer;
-          transition: background 0.2s;
-        }
-        .btn-save-pane:hover {
-          background: #1d4ed8;
-        }
-
-        /* Task Provider Routing Styles */
-        .mappings-grid {
-          display: grid;
-          grid-template-columns: 1fr;
-          gap: 1rem;
-          margin-top: 1rem;
-        }
-        @media (min-width: 768px) {
-          .mappings-grid {
-            grid-template-columns: 1fr 1fr;
-          }
-        }
-        .mapping-card {
-          border: 1px solid #e5e7eb;
-          background: #f9fafb;
-          border-radius: 8px;
-          padding: 1rem;
-          display: flex;
-          flex-direction: column;
-          justify-content: space-between;
-          gap: 0.75rem;
-        }
-        .mapping-info {
-          display: flex;
-          flex-direction: column;
-          gap: 0.25rem;
-          font-size: 0.8125rem;
-        }
-        .mapping-info strong {
-          font-size: 0.875rem;
-          color: #111;
-        }
-        .mapping-card select {
-          padding: 0.375rem 0.5rem;
-          font-size: 0.8125rem;
-          border: 1px solid #ccc;
-          border-radius: 4px;
-          background: #fff;
-          width: 100%;
-        }
-        .text-gray {
-          color: #6b7280;
-        }
-      `}</style>
     </div>
   );
 }

apps/gui/src/app/globals.css

@@ -1,18 +1,10 @@
-*,
-*::before,
-*::after {
-  box-sizing: border-box;
-  margin: 0;
-  padding: 0;
-}
+@tailwind base;
+@tailwind components;
+@tailwind utilities;
 
-html {
-  font-family: system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto,
-    Oxygen, Ubuntu, Cantarell, sans-serif;
-  color: #111;
-  background: #fafafa;
-}
-
-body {
-  min-height: 100dvh;
+@layer base {
+  html {
+    font-family: system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI",
+      Roboto, Oxygen, Ubuntu, Cantarell, sans-serif;
+  }
 }

apps/gui/src/app/layout.tsx

@@ -10,7 +10,7 @@ export const metadata = {
 export default function RootLayout({ children }: { children: ReactNode }) {
   return (
     <html lang="en">
-      <body>
+      <body className="min-h-dvh bg-[#fafafa] text-[#111]">
         <NavBar />
         {children}
       </body>

apps/gui/src/app/page.tsx

@@ -2,62 +2,31 @@ import Link from "next/link";
 
 export default function Home() {
   return (
-    <main className="home">
-      <h1>Omnia GUI</h1>
-      <p className="subtitle">
+    <main className="mx-auto max-w-[800px] px-4 py-12">
+      <h1 className="mb-2 text-3xl">Omnia GUI</h1>
+      <p className="mb-8 text-gray-500">
         Configuration and gameplay interface for the Omnia simulation engine.
       </p>
-      <div className="home-links">
-        <Link href="/play" className="home-card">
-          <h2>Play</h2>
-          <p>Start a simulation and interact with NPCs</p>
+      <div className="flex gap-4">
+        <Link
+          href="/play"
+          className="block flex-1 rounded-lg border border-gray-200 p-6 text-inherit no-underline transition-[border-color,box-shadow] duration-150 hover:border-blue-600 hover:shadow-[0_2px_8px_rgba(37,99,235,0.1)]"
+        >
+          <h2 className="mb-1 text-xl">Play</h2>
+          <p className="text-sm text-gray-500">
+            Start a simulation and interact with NPCs
+          </p>
         </Link>
-        <Link href="/config" className="home-card">
-          <h2>Config</h2>
-          <p>Check environment, API keys, and available scenarios</p>
+        <Link
+          href="/config"
+          className="block flex-1 rounded-lg border border-gray-200 p-6 text-inherit no-underline transition-[border-color,box-shadow] duration-150 hover:border-blue-600 hover:shadow-[0_2px_8px_rgba(37,99,235,0.1)]"
+        >
+          <h2 className="mb-1 text-xl">Config</h2>
+          <p className="text-sm text-gray-500">
+            Check environment, API keys, and available scenarios
+          </p>
         </Link>
       </div>
-      <style>{`
-        .home {
-          max-width: 800px;
-          margin: 0 auto;
-          padding: 3rem 1rem;
-        }
-        .home h1 {
-          font-size: 2rem;
-          margin-bottom: 0.5rem;
-        }
-        .subtitle {
-          color: #555;
-          margin-bottom: 2rem;
-        }
-        .home-links {
-          display: flex;
-          gap: 1rem;
-        }
-        .home-card {
-          flex: 1;
-          display: block;
-          padding: 1.5rem;
-          border: 1px solid #e5e7eb;
-          border-radius: 8px;
-          text-decoration: none;
-          color: inherit;
-          transition: border-color 0.15s, box-shadow 0.15s;
-        }
-        .home-card:hover {
-          border-color: #2563eb;
-          box-shadow: 0 2px 8px rgba(37, 99, 235, 0.1);
-        }
-        .home-card h2 {
-          font-size: 1.25rem;
-          margin-bottom: 0.25rem;
-        }
-        .home-card p {
-          font-size: 0.875rem;
-          color: #555;
-        }
-      `}</style>
     </main>
   );
 }

apps/gui/src/app/play/actions.ts

@@ -4,7 +4,7 @@ import path from "path";
 import fs from "fs";
 import { simulationManager } from "@/lib/simulation";
 import type { SimSnapshot } from "@/lib/simulation";
-import { ProviderManager, LLMProviderInstance } from "@omnia/llm";
+import { ProviderManager, ModelProviderInstance, AVAILABLE_PROVIDERS, ModelProviderMeta } from "@omnia/llm";
 
 function resolveScenarioPath(relative: string): string {
   const cwd = process.cwd();
@@ -233,7 +233,7 @@ export async function deleteSimulation(simId: string): Promise<
   }
 }
 
-export async function listProviderInstances(): Promise<LLMProviderInstance[]> {
+export async function listProviderInstances(): Promise<ModelProviderInstance[]> {
   return ProviderManager.list();
 }
 
@@ -242,8 +242,9 @@ export async function createProviderInstance(
   providerName: string,
   apiKey: string,
   modelName?: string,
-): Promise<LLMProviderInstance> {
-  return ProviderManager.create(name, providerName, apiKey, modelName);
+  type: "generative" | "embedding" = "generative",
+): Promise<ModelProviderInstance> {
+  return ProviderManager.create(name, providerName, apiKey, modelName, type);
 }
 
 export async function deleteProviderInstance(id: string): Promise<void> {
@@ -260,8 +261,9 @@ export async function updateProviderInstance(
   providerName: string,
   apiKey?: string,
   modelName?: string,
+  type: "generative" | "embedding" = "generative",
 ): Promise<void> {
-  ProviderManager.update(id, name, providerName, apiKey, modelName);
+  ProviderManager.update(id, name, providerName, apiKey, modelName, type);
 }
 
 export async function getProviderMappings(): Promise<Record<string, string>> {
@@ -274,3 +276,11 @@ export async function setProviderMapping(
 ): Promise<void> {
   ProviderManager.setMapping(task, providerInstanceId);
 }
+
+export async function getAvailableProviders(): Promise<ModelProviderMeta[]> {
+  return AVAILABLE_PROVIDERS;
+}
+
+export async function regenerateEmbeddings(newProviderInstanceId?: string): Promise<void> {
+  await simulationManager.regenerateAllEmbeddings(newProviderInstanceId);
+}

apps/gui/src/lib/simulation.ts

@@ -17,7 +17,7 @@ for (const c of envCandidates) {
   }
 }
 
-import { BufferRepository } from "@omnia/memory";
+import { BufferRepository, LedgerRepository } from "@omnia/memory";
 import { Architect, AliasDeltaGenerator } from "@omnia/architect";
 import {
   ActorAgent,
@@ -25,7 +25,7 @@ import {
   IActorProseGenerator,
   buildBufferEntryForIntent,
 } from "@omnia/actor";
-import { GeminiProvider, ILLMProvider, MockLLMProvider, ProviderManager } from "@omnia/llm";
+import { GeminiProvider, ILLMProvider, MockLLMProvider, ProviderManager, OpenRouterProvider, IEmbeddingProvider, GeminiEmbeddingProvider, MockEmbeddingProvider, ModelProviderInstance } from "@omnia/llm";
 import { ScenarioLoader } from "@omnia/scenario";
 
 import type {
@@ -89,6 +89,7 @@ interface SimSession {
   dbPath: string;
   coreRepo: SQLiteRepository;
   bufferRepo: BufferRepository;
+  ledgerRepo: LedgerRepository;
   worldInstanceId: string;
   scenarioName: string;
   scenarioDescription: string;
@@ -101,6 +102,7 @@ interface SimSession {
   validatorProvider: ILLMProvider;
   decoderProvider: ILLMProvider;
   timedeltaProvider: ILLMProvider;
+  embeddingProvider: IEmbeddingProvider;
   architect: Architect;
   aliasGenerator: AliasDeltaGenerator;
   log: LogEntry[];
@@ -119,14 +121,14 @@ class SimulationManager {
     playEntityName?: string,
     providerInstanceId?: string,
   ): Promise<SimSnapshot> {
-    let activeInstance = providerInstanceId
-      ? ProviderManager.list().find((p) => p.id === providerInstanceId)
-      : ProviderManager.getActive();
+    let activeInstance: ModelProviderInstance | null = providerInstanceId
+      ? ProviderManager.list().find((p) => p.id === providerInstanceId) || null
+      : ProviderManager.getActive("generative");
 
     if (!activeInstance) {
       const envKey = process.env.GOOGLE_API_KEY;
       if (envKey) {
-        activeInstance = ProviderManager.create("Default (Env)", "google-genai", envKey);
+        activeInstance = ProviderManager.create("Default (Env)", "google-genai", envKey, undefined, "generative");
       }
     }
 
@@ -154,6 +156,7 @@ class SimulationManager {
     const db = new Database(dbPath);
     const coreRepo = new SQLiteRepository(db);
     const bufferRepo = new BufferRepository(db);
+    const ledgerRepo = new LedgerRepository(db);
     const loader = new ScenarioLoader(coreRepo, bufferRepo);
 
     const worldInstanceId = id;
@@ -219,30 +222,52 @@ class SimulationManager {
     }
 
     const list = ProviderManager.list();
-    const active = ProviderManager.getActive() || activeInstance;
+    const active = ProviderManager.getActive("generative") || activeInstance;
     const mappings = ProviderManager.getMappings();
 
     const resolveProviderForTask = (task: string): ILLMProvider => {
       const mappedId = mappings[task];
       let inst = mappedId ? list.find((p) => p.id === mappedId) : null;
-      if (!inst) {
+      if (!inst || inst.type !== "generative") {
         inst = active;
       }
 
       const key = inst ? inst.apiKey : (process.env.GOOGLE_API_KEY || "");
       const providerName = inst ? inst.providerName : "google-genai";
+      const modelName = inst ? inst.modelName : undefined;
 
       if (providerName === "google-genai") {
-        return new GeminiProvider(key);
+        return new GeminiProvider(key, modelName);
+      } else if (providerName === "openrouter") {
+        return new OpenRouterProvider(key, modelName);
       } else {
         return new MockLLMProvider([]);
       }
     };
 
+    const resolveEmbeddingProvider = (): IEmbeddingProvider => {
+      const mappedId = mappings["embeddings"];
+      let inst = mappedId ? list.find((p) => p.id === mappedId) : null;
+      if (!inst || inst.type !== "embedding") {
+        inst = ProviderManager.getActive("embedding");
+      }
+
+      const key = inst ? inst.apiKey : (process.env.GOOGLE_API_KEY || "");
+      const providerName = inst ? inst.providerName : "google-genai";
+      const modelName = inst ? inst.modelName : undefined;
+
+      if (providerName === "google-genai") {
+        return new GeminiEmbeddingProvider(key, modelName);
+      } else {
+        return new MockEmbeddingProvider(modelName);
+      }
+    };
+
     const actorProvider = resolveProviderForTask("actor-prose");
     const validatorProvider = resolveProviderForTask("llm-validator");
     const decoderProvider = resolveProviderForTask("intent-decoder");
     const timedeltaProvider = resolveProviderForTask("timedelta");
+    const embeddingProvider = resolveEmbeddingProvider();
 
     const architect = new Architect(
       { validator: validatorProvider, timedelta: timedeltaProvider },
@@ -255,9 +280,10 @@ class SimulationManager {
       dbPath,
       coreRepo,
       bufferRepo,
-      worldInstanceId,
+      ledgerRepo,
+      worldInstanceId: worldInstanceId,
       scenarioName: scenarioJson.name,
-      scenarioDescription: scenarioJson.description,
+      scenarioDescription: scenarioJson.description || "",
       turn: 1,
       maxTurns: 20,
       entities: entityInfos,
@@ -267,6 +293,7 @@ class SimulationManager {
       validatorProvider,
       decoderProvider,
       timedeltaProvider,
+      embeddingProvider,
       architect,
       aliasGenerator,
       log: [],
@@ -350,6 +377,7 @@ class SimulationManager {
       const playerActor = new ActorAgent(
         { actor: session.actorProvider, decoder: session.decoderProvider },
         session.bufferRepo,
+        session.ledgerRepo,
         20,
         new FixedProseGenerator(prose),
       );
@@ -460,7 +488,7 @@ class SimulationManager {
     const entity = worldState.getEntity(info.id);
     if (!entity) throw new Error(`Entity "${info.id}" not found`);
 
-    const promptBuilder = new ActorPromptBuilder(session.bufferRepo, 20);
+    const promptBuilder = new ActorPromptBuilder(session.bufferRepo, session.ledgerRepo, 20);
     const { systemPrompt, userContext } = promptBuilder.build(
       worldState,
       entity,
@@ -490,6 +518,7 @@ class SimulationManager {
     const actor = new ActorAgent(
       { actor: session.actorProvider, decoder: session.decoderProvider },
       session.bufferRepo,
+      session.ledgerRepo,
       20,
     );
     const result = await actor.act(worldState, entity);
@@ -647,19 +676,19 @@ class SimulationManager {
       }
 
       const list = ProviderManager.list();
-      const active = ProviderManager.getActive();
+      const active = ProviderManager.getActive("generative");
       const mappings = state.providerMappings || {};
 
       const resolveProviderForTask = (task: string): ILLMProvider => {
         const mappedId = mappings[task];
         let inst = mappedId ? list.find((p) => p.id === mappedId) : null;
-        if (!inst) {
+        if (!inst || inst.type !== "generative") {
           inst = active;
         }
         if (!inst) {
           const envKey = process.env.GOOGLE_API_KEY;
           if (envKey) {
-            inst = ProviderManager.create("Default (Env)", "google-genai", envKey);
+            inst = ProviderManager.create("Default (Env)", "google-genai", envKey, undefined, "generative");
           }
         }
 
@@ -668,19 +697,47 @@ class SimulationManager {
         }
 
         if (inst.providerName === "google-genai") {
-          return new GeminiProvider(inst.apiKey);
+          return new GeminiProvider(inst.apiKey, inst.modelName);
+        } else if (inst.providerName === "openrouter") {
+          return new OpenRouterProvider(inst.apiKey, inst.modelName);
         } else {
           return new MockLLMProvider([]);
         }
       };
 
+      const resolveEmbeddingProvider = (): IEmbeddingProvider => {
+        const mappedId = mappings["embeddings"];
+        let inst = mappedId ? list.find((p) => p.id === mappedId) : null;
+        if (!inst || inst.type !== "embedding") {
+          inst = ProviderManager.getActive("embedding");
+        }
+        if (!inst) {
+          const envKey = process.env.GOOGLE_API_KEY;
+          if (envKey) {
+            inst = ProviderManager.create("Default Embed (Env)", "google-genai", envKey, "gemini-embedding-001", "embedding");
+          }
+        }
+
+        if (!inst) {
+          throw new Error(`No active Embedding Provider Instance found for task "embeddings". Please configure an embedding key in Settings first.`);
+        }
+
+        if (inst.providerName === "google-genai") {
+          return new GeminiEmbeddingProvider(inst.apiKey, inst.modelName);
+        } else {
+          return new MockEmbeddingProvider(inst.modelName);
+        }
+      };
+
       const coreRepo = new SQLiteRepository(db);
       const bufferRepo = new BufferRepository(db);
+      const ledgerRepo = new LedgerRepository(db);
 
       const actorProvider = resolveProviderForTask("actor-prose");
       const validatorProvider = resolveProviderForTask("llm-validator");
       const decoderProvider = resolveProviderForTask("intent-decoder");
       const timedeltaProvider = resolveProviderForTask("timedelta");
+      const embeddingProvider = resolveEmbeddingProvider();
 
       const architect = new Architect(
         { validator: validatorProvider, timedelta: timedeltaProvider },
@@ -693,6 +750,7 @@ class SimulationManager {
         dbPath,
         coreRepo,
         bufferRepo,
+        ledgerRepo,
         worldInstanceId: id,
         scenarioName: state.scenarioName,
         scenarioDescription: state.scenarioDescription,
@@ -705,6 +763,7 @@ class SimulationManager {
         validatorProvider,
         decoderProvider,
         timedeltaProvider,
+        embeddingProvider,
         architect,
         aliasGenerator,
         log: state.log || [],
@@ -772,6 +831,53 @@ class SimulationManager {
     });
   }
 
+  async regenerateAllEmbeddings(newProviderInstanceId?: string): Promise<void> {
+    const dbDir = path.resolve(process.cwd(), "data");
+    if (!fs.existsSync(dbDir)) return;
+
+    const files = fs.readdirSync(dbDir).filter(f => f.startsWith("sim-") && f.endsWith(".db"));
+
+    const list = ProviderManager.list();
+    let inst = newProviderInstanceId ? list.find((p) => p.id === newProviderInstanceId) : null;
+    if (!inst || inst.type !== "embedding") {
+      inst = ProviderManager.getActive("embedding");
+    }
+
+    const key = inst ? inst.apiKey : (process.env.GOOGLE_API_KEY || "");
+    const providerName = inst ? inst.providerName : "google-genai";
+    const modelName = inst ? inst.modelName : undefined;
+
+    let embeddingProvider: IEmbeddingProvider;
+    if (providerName === "google-genai") {
+      embeddingProvider = new GeminiEmbeddingProvider(key, modelName);
+    } else {
+      embeddingProvider = new MockEmbeddingProvider(modelName);
+    }
+
+    for (const file of files) {
+      const dbPath = path.join(dbDir, file);
+      const id = file.replace(".db", "");
+      const activeSession = this.sessions.get(id);
+      const db = activeSession ? activeSession.db : new Database(dbPath);
+
+      try {
+        const rows = db.prepare(`SELECT id, content FROM ledger_entries`).all() as { id: string; content: string }[];
+        
+        for (const row of rows) {
+          const vector = await embeddingProvider.embed(row.content);
+          const buffer = Buffer.from(new Float32Array(vector).buffer);
+          db.prepare(`UPDATE ledger_entries SET embedding = ? WHERE id = ?`).run(buffer, row.id);
+        }
+      } catch (err) {
+        console.error(`Failed to regenerate embeddings for ${file}:`, err);
+      } finally {
+        if (!activeSession) {
+          db.close();
+        }
+      }
+    }
+  }
+
   private save(session: SimSession): void {
     const state: SavedState = {
       scenarioName: session.scenarioName,

apps/gui/tailwind.config.ts

@@ -0,0 +1,11 @@
+import type { Config } from "tailwindcss";
+
+const config: Config = {
+  content: ["./src/**/*.{js,ts,jsx,tsx,mdx}"],
+  theme: {
+    extend: {},
+  },
+  plugins: [],
+};
+
+export default config;

package.json

@@ -8,7 +8,6 @@
     "build:web": "pnpm --filter landing build",
     "build:docs": "pnpm --filter docs build",
     "build:gui": "pnpm --filter @omnia/gui build",
-    "build:all": "pnpm build && pnpm build:web && pnpm build:docs && pnpm build:gui",
     "dev:web": "pnpm --filter landing dev",
     "dev:docs": "pnpm --filter docs dev",
     "dev:gui": "pnpm --filter @omnia/gui dev",
@@ -23,8 +22,8 @@
     "test:evals": "vitest run --project evals"
   },
   "keywords": [],
-  "author": "",
-  "license": "ISC",
+  "author": "sortedcord",
+  "license": "MIT",
   "devEngines": {
     "packageManager": {
       "name": "pnpm",
@@ -48,6 +47,7 @@
   },
   "dependencies": {
     "@langchain/google-genai": "^2.2.0",
+    "@langchain/openrouter": "^0.4.3",
     "@types/node": "^20.19.43",
     "dotenv": "^17.4.2"
   }

packages/actor/src/actor-prompt-builder.ts

@@ -9,6 +9,8 @@ import {
   BufferEntry,
   BufferRepository,
   serializeSubjectiveBufferEntry,
+  LedgerEntry,
+  LedgerRepository,
 } from "@omnia/memory";
 
 /**
@@ -37,12 +39,17 @@ export class ActorPromptBuilder {
   /**
    * @param bufferRepo  Used to fetch the actor's recent memory. Optional —
    *                    if absent, the memory section is omitted.
+   * @param ledgerRepo  Used to fetch long-term memories. Optional.
    * @param memoryLimit Maximum number of recent buffer entries to inject.
    *                    Defaults to 20.
+   * @param ledgerLimit Maximum number of long-term memories to retrieve.
+   *                    Defaults to 5.
    */
   constructor(
     private bufferRepo?: BufferRepository,
+    private ledgerRepo?: LedgerRepository,
     private memoryLimit = 20,
+    private ledgerLimit = 5,
   ) {}
 
   /**
@@ -74,15 +81,14 @@ Guidelines:
 - Keep your prose vivid but concise. A single response may contain more than one intent (e.g., you may think, then speak, then act) — write them in natural narrative order.
 - Not every response requires an outward action. It is perfectly valid to only think (a monologue) and do nothing perceivable.
 - Never speak or act on another entity's behalf — you only control your own character.
-".
 `.trim();
   }
 
   private buildUserContext(worldState: WorldState, entity: Entity): string {
     const sections: string[] = [];
+    const now = worldState.clock.get();
 
     // --- Subjective present time ---
-    const now = worldState.clock.get();
     sections.push(
       `=== CURRENT MOMENT ===\nIt is ${now.toISOString()} right now.`,
     );
@@ -92,30 +98,43 @@ Guidelines:
       `=== THE WORLD AS YOU PERCEIVE IT ===\n${serializeSubjectiveWorldState(worldState, entity.id)}`,
     );
 
+    // Fetch recent buffer entries once
+    let recentEntries: BufferEntry[] = [];
+    if (this.bufferRepo) {
+      try {
+        recentEntries = this.bufferRepo.listForOwner(entity.id);
+      } catch {}
+    }
+
     // --- Recent memory ---
-    const memorySection = this.buildMemorySection(
-      entity,
-      worldState.clock.get(),
-    );
+    const memorySection = this.buildMemorySection(entity, recentEntries, now);
     if (memorySection) {
       sections.push(memorySection);
     }
 
+    // --- Recalled Long-Term memory ---
+    const ledgerSection = this.buildLedgerSection(
+      worldState,
+      entity,
+      recentEntries,
+      now,
+    );
+    if (ledgerSection) {
+      sections.push(ledgerSection);
+    }
+
     return sections.join("\n\n");
   }
 
-  private buildMemorySection(entity: Entity, now: Date): string | null {
+  private buildMemorySection(
+    entity: Entity,
+    entries: BufferEntry[],
+    now: Date,
+  ): string | null {
     if (!this.bufferRepo) return null;
 
-    let entries: BufferEntry[];
-    try {
-      entries = this.bufferRepo.listForOwner(entity.id);
-    } catch {
-      return null;
-    }
-
     if (entries.length === 0) {
-      return `=== YOUR RECENT MEMORY ===\n(You have no memories yet.)`;
+      return `=== RECENT EVENTS ===\n(No recent events recorded.)`;
     }
 
     const recent = entries.slice(-this.memoryLimit);
@@ -135,6 +154,110 @@ Guidelines:
       groupedLines.push(`  - ${serialized}`);
     }
 
-    return `=== YOUR RECENT MEMORY ===\n${groupedLines.join("\n")}`;
+    return `=== RECENT EVENTS ===\n${groupedLines.join("\n")}`;
+  }
+
+  private buildLedgerSection(
+    worldState: WorldState,
+    entity: Entity,
+    recentBuffer: BufferEntry[],
+    now: Date,
+  ): string | null {
+    if (!this.ledgerRepo) return null;
+
+    // 1. Get co-located entities (in the same location as entity)
+    const coLocatedEntityIds: string[] = [];
+    if (entity.locationId) {
+      for (const e of worldState.entities.values()) {
+        if (e.id !== entity.id && e.locationId === entity.locationId) {
+          coLocatedEntityIds.push(e.id);
+        }
+      }
+    }
+
+    // 2. Compute Active Focus entities based on recent interactions (last 10 entries)
+    const activeFocus = new Set<string>();
+    const maxFocus = 3;
+
+    // We scan the recent buffer entries to see who we recently talked to or who talked to us
+    for (let i = recentBuffer.length - 1; i >= 0; i--) {
+      const entry = recentBuffer[i];
+      const intent = entry.intent;
+
+      if (
+        intent.actorId !== entity.id &&
+        coLocatedEntityIds.includes(intent.actorId)
+      ) {
+        activeFocus.add(intent.actorId);
+      }
+      for (const targetId of intent.targetIds) {
+        if (targetId !== entity.id && coLocatedEntityIds.includes(targetId)) {
+          activeFocus.add(targetId);
+        }
+      }
+      if (activeFocus.size >= maxFocus) break;
+    }
+
+    // If co-located entities is small, auto-focus all of them
+    if (activeFocus.size < maxFocus && coLocatedEntityIds.length <= maxFocus) {
+      for (const id of coLocatedEntityIds) {
+        if (id !== entity.id) {
+          activeFocus.add(id);
+        }
+      }
+    }
+
+    const activeFocusIds = Array.from(activeFocus);
+
+    // 3. Retrieve memories using Active Focus
+    let recalled: LedgerEntry[];
+    try {
+      recalled = this.ledgerRepo.retrieve(
+        entity.id,
+        entity.locationId,
+        activeFocusIds,
+        undefined, // no query embedding for now (Recency + Importance ranking)
+        now,
+        this.ledgerLimit,
+        { includeAssociativeNeighbors: true },
+      );
+    } catch {
+      return null;
+    }
+
+    if (recalled.length === 0) return null;
+
+    // 4. Format them identical to the recent memory format
+    const groupedLines: string[] = [];
+    let currentGroup: string | null = null;
+
+    for (const entry of recalled) {
+      const when = naturalizeTime(now, new Date(entry.timestamp));
+
+      let content = entry.content;
+      // Resolve system IDs to subjective aliases in the content
+      for (const targetId of entry.involvedEntityIds) {
+        const alias = entity.aliases.get(targetId) ?? targetId;
+        content = content.replace(new RegExp(targetId, "g"), alias);
+      }
+      if (entry.locationId) {
+        content += ` (at ${entry.locationId})`;
+      }
+
+      if (when !== currentGroup) {
+        currentGroup = when;
+        const header = when.charAt(0).toUpperCase() + when.slice(1);
+        groupedLines.push(header);
+      }
+
+      groupedLines.push(`  - ${content}`);
+      if (entry.quotes && entry.quotes.length > 0) {
+        for (const quote of entry.quotes) {
+          groupedLines.push(`    Quote: "${quote}"`);
+        }
+      }
+    }
+
+    return `=== YOUR MEMORIES ===\n${groupedLines.join("\n")}`;
   }
 }

packages/actor/src/actor.ts

@@ -3,6 +3,7 @@ import { ILLMProvider } from "@omnia/llm";
 import {
   BufferEntry,
   BufferRepository,
+  LedgerRepository,
 } from "@omnia/memory";
 import {
   Intent,
@@ -73,6 +74,7 @@ export class ActorAgent {
   constructor(
     llmProvider: ILLMProvider | { actor: ILLMProvider; decoder: ILLMProvider },
     bufferRepo?: BufferRepository,
+    ledgerRepo?: LedgerRepository,
     memoryLimit?: number,
     generator?: IActorProseGenerator,
   ) {
@@ -87,7 +89,7 @@ export class ActorAgent {
       decoderProv = llmProvider;
     }
 
-    this.promptBuilder = new ActorPromptBuilder(bufferRepo, memoryLimit);
+    this.promptBuilder = new ActorPromptBuilder(bufferRepo, ledgerRepo, memoryLimit);
     this.decoder = new IntentDecoder(decoderProv);
     this.generator = generator ?? new LLMActorProseGenerator(actorProv);
     this.llmProvider = actorProv;

packages/actor/tests/actor-prompt-builder.test.ts

@@ -0,0 +1,100 @@
+import { describe, it, expect, beforeEach, afterEach } from "vitest";
+import Database from "better-sqlite3";
+import { WorldState, Entity, AttributeVisibility } from "@omnia/core";
+import { BufferRepository, LedgerRepository } from "@omnia/memory";
+import { ActorPromptBuilder } from "../src/actor-prompt-builder";
+
+describe("ActorPromptBuilder with Long-Term Memory Integration", () => {
+  let db: Database.Database;
+  let bufferRepo: BufferRepository;
+  let ledgerRepo: LedgerRepository;
+
+  beforeEach(() => {
+    db = new Database(":memory:");
+    
+    // Core database schemas for testing
+    db.exec(`
+      CREATE TABLE objects (
+        id TEXT PRIMARY KEY
+      );
+    `);
+
+    db.exec(`
+      INSERT INTO objects (id) VALUES ('alice'), ('bob'), ('charlie');
+    `);
+
+    bufferRepo = new BufferRepository(db);
+    ledgerRepo = new LedgerRepository(db);
+  });
+
+  afterEach(() => {
+    db.close();
+  });
+
+  it("should inject both recent memory and recalled long-term memory with subjective aliases resolved", () => {
+    const world = new WorldState("world-123", new Date("2024-01-10T12:00:00.000Z"));
+    
+    const alice = new Entity("alice", "tavern");
+    // Add subjective alias for bob
+    alice.aliases.set("bob", "Strider");
+    world.addEntity(alice);
+
+    const bob = new Entity("bob", "tavern");
+    world.addEntity(bob);
+
+    // 1. Populate recent buffer memory
+    bufferRepo.save({
+      id: "buf1",
+      ownerId: "alice",
+      timestamp: "2024-01-10T11:58:00.000Z", // 2 mins ago
+      locationId: "tavern",
+      intent: {
+        type: "dialogue",
+        actorId: "alice",
+        targetIds: ["bob"],
+        originalText: "Hello there",
+        description: "Alice greets Bob",
+      },
+    });
+
+    // 2. Populate ledger repository (long-term memory)
+    ledgerRepo.save({
+      id: "ledger1",
+      ownerId: "alice",
+      timestamp: "2024-01-08T12:00:00.000Z", // 2 days ago
+      locationId: "tavern",
+      involvedEntityIds: ["bob"],
+      content: "alice met bob at the tavern.",
+      quotes: ["I am a ranger."],
+      importance: 9,
+      embedding: [],
+    });
+
+    const builder = new ActorPromptBuilder(bufferRepo, ledgerRepo, 20, 5);
+    const { userContext } = builder.build(world, alice);
+
+    // Check recent memory exists
+    expect(userContext).toContain("=== RECENT EVENTS ===");
+    expect(userContext).toContain("Alice greets Bob");
+    // Bob should be resolved to Strider
+    expect(userContext).toContain("spoke to Strider");
+
+    // Check long-term memory exists
+    expect(userContext).toContain("=== YOUR MEMORIES ===");
+    // Bob should be resolved to Strider in the ledger content
+    expect(userContext).toContain("alice met Strider at the tavern.");
+    expect(userContext).toContain('Quote: "I am a ranger."');
+  });
+
+  it("should not explode if ledger contains no memories or is empty", () => {
+    const world = new WorldState("world-123", new Date("2024-01-10T12:00:00.000Z"));
+    const alice = new Entity("alice", "tavern");
+    world.addEntity(alice);
+
+    const builder = new ActorPromptBuilder(bufferRepo, ledgerRepo, 20, 5);
+    const { userContext } = builder.build(world, alice);
+
+    expect(userContext).toContain("=== RECENT EVENTS ===");
+    expect(userContext).not.toContain("=== YOUR MEMORIES ===");
+  });
+});

packages/llm/src/config.ts

@@ -2,6 +2,7 @@ import { z } from "zod";
 
 const LLMConfigSchema = z.object({
   GOOGLE_API_KEY: z.string().optional(),
+  OPENROUTER_API_KEY: z.string().optional(),
 });
 
 export const llmConfig = LLMConfigSchema.parse(process.env);

packages/llm/src/index.ts

@@ -2,4 +2,5 @@ export * from "./llm.js";
 export * from "./config.js";
 export * from "./providers/google-genai.js";
 export * from "./providers/mock.js";
+export * from "./providers/openrouter.js";
 export * from "./provider-manager.js";

packages/llm/src/llm.ts

@@ -30,18 +30,55 @@ export interface LLMCallRecord {
 
 export interface ILLMProvider {
   providerName: string;
-  // We use Zod to ensure the generic T matches the schema
   generateStructuredResponse<T extends z.ZodTypeAny>(
     request: LLMRequest<T>,
   ): Promise<LLMResponse<z.infer<T>>>;
   lastCalls?: LLMCallRecord[];
 }
 
-export interface LLMProviderInstance {
+export interface IEmbeddingProvider {
+  providerName: string;
+  embed(text: string): Promise<number[]>;
+}
+
+export interface ModelProviderInstance {
   id: string;
   name: string;
   providerName: string;
   apiKey: string;
   isActive: boolean;
   modelName?: string;
+  type: "generative" | "embedding";
 }
+
+export interface ModelProviderMeta {
+  id: string;
+  displayName: string;
+  description: string;
+  defaultModel: string;
+  defaultEmbeddingModel: string;
+}
+
+export const AVAILABLE_PROVIDERS: ModelProviderMeta[] = [
+  {
+    id: "google-genai",
+    displayName: "Google Gemini",
+    description: "Official Gemini integration using Google Gen AI SDK",
+    defaultModel: "gemini-2.5-flash",
+    defaultEmbeddingModel: "gemini-embedding-001",
+  },
+  {
+    id: "openrouter",
+    displayName: "OpenRouter",
+    description: "Multi-model router supporting Anthropic, OpenAI, DeepSeek, and local models",
+    defaultModel: "google/gemini-2.5-flash",
+    defaultEmbeddingModel: "openai/text-embedding-3-small",
+  },
+  {
+    id: "mock",
+    displayName: "Mock LLM Provider",
+    description: "Stateless mock provider for testing and offline development",
+    defaultModel: "mock",
+    defaultEmbeddingModel: "mock-embeddings",
+  },
+];

packages/llm/src/provider-manager.ts

@@ -1,7 +1,7 @@
 import Database from "better-sqlite3";
 import path from "path";
 import fs from "fs";
-import type { LLMProviderInstance } from "./llm.js";
+import type { ModelProviderInstance } from "./llm.js";
 
 function getWorkspaceRoot() {
   let current = process.cwd();
@@ -35,7 +35,8 @@ function getSettingsDb() {
       providerName TEXT NOT NULL,
       apiKey TEXT NOT NULL,
       isActive INTEGER NOT NULL DEFAULT 0,
-      modelName TEXT
+      modelName TEXT,
+      type TEXT NOT NULL DEFAULT 'generative'
     )
   `).run();
 
@@ -44,12 +45,18 @@ function getSettingsDb() {
   } catch {
     // ignore
   }
+
+  try {
+    db.prepare(`ALTER TABLE provider_instances ADD COLUMN type TEXT NOT NULL DEFAULT 'generative'`).run();
+  } catch {
+    // ignore
+  }
   
   return db;
 }
 
 export class ProviderManager {
-  static list(): LLMProviderInstance[] {
+  static list(): ModelProviderInstance[] {
     const db = getSettingsDb();
     try {
       const rows = db.prepare(`SELECT * FROM provider_instances`).all() as {
@@ -59,6 +66,7 @@ export class ProviderManager {
         apiKey: string;
         isActive: number;
         modelName?: string;
+        type: string;
       }[];
       return rows.map((r) => ({
         id: r.id,
@@ -67,25 +75,34 @@ export class ProviderManager {
         apiKey: r.apiKey,
         isActive: r.isActive === 1,
         modelName: r.modelName || undefined,
+        type: (r.type as "generative" | "embedding") || "generative",
       }));
     } finally {
       db.close();
     }
   }
 
-  static create(name: string, providerName: string, apiKey: string, modelName?: string): LLMProviderInstance {
+  static create(
+    name: string,
+    providerName: string,
+    apiKey: string,
+    modelName?: string,
+    type: "generative" | "embedding" = "generative"
+  ): ModelProviderInstance {
     const db = getSettingsDb();
     try {
       const id = "provider-" + Date.now();
-      const activeCount = db.prepare(`SELECT COUNT(*) as count FROM provider_instances WHERE isActive = 1`).get() as { count: number };
+      const activeCount = db
+        .prepare(`SELECT COUNT(*) as count FROM provider_instances WHERE isActive = 1 AND type = ?`)
+        .get(type) as { count: number };
       const isActive = activeCount.count === 0 ? 1 : 0;
       
       db.prepare(`
-        INSERT INTO provider_instances (id, name, providerName, apiKey, isActive, modelName)
-        VALUES (?, ?, ?, ?, ?, ?)
-      `).run(id, name, providerName, apiKey, isActive, modelName || null);
+        INSERT INTO provider_instances (id, name, providerName, apiKey, isActive, modelName, type)
+        VALUES (?, ?, ?, ?, ?, ?, ?)
+      `).run(id, name, providerName, apiKey, isActive, modelName || null, type);
       
-      return { id, name, providerName, apiKey, isActive: isActive === 1, modelName };
+      return { id, name, providerName, apiKey, isActive: isActive === 1, modelName, type };
     } finally {
       db.close();
     }
@@ -94,11 +111,13 @@ export class ProviderManager {
   static delete(id: string): void {
     const db = getSettingsDb();
     try {
-      const provider = db.prepare(`SELECT isActive FROM provider_instances WHERE id = ?`).get(id) as { isActive: number } | undefined;
+      const provider = db.prepare(`SELECT isActive, type FROM provider_instances WHERE id = ?`).get(id) as { isActive: number; type: string } | undefined;
       db.prepare(`DELETE FROM provider_instances WHERE id = ?`).run(id);
       
       if (provider && provider.isActive === 1) {
-        const next = db.prepare(`SELECT id FROM provider_instances LIMIT 1`).get() as { id: string } | undefined;
+        const next = db
+          .prepare(`SELECT id FROM provider_instances WHERE type = ? LIMIT 1`)
+          .get(provider.type) as { id: string } | undefined;
         if (next) {
           db.prepare(`UPDATE provider_instances SET isActive = 1 WHERE id = ?`).run(next.id);
         }
@@ -111,60 +130,85 @@ export class ProviderManager {
   static setActive(id: string): void {
     const db = getSettingsDb();
     try {
-      db.prepare(`UPDATE provider_instances SET isActive = 0`).run();
-      db.prepare(`UPDATE provider_instances SET isActive = 1 WHERE id = ?`).run(id);
-    } finally {
-      db.close();
-    }
-  }
-
-  static update(id: string, name: string, providerName: string, apiKey?: string, modelName?: string): void {
-    const db = getSettingsDb();
-    try {
-      if (apiKey && apiKey.trim()) {
-        db.prepare(`
-          UPDATE provider_instances
-          SET name = ?, providerName = ?, apiKey = ?, modelName = ?
-          WHERE id = ?
-        `).run(name, providerName, apiKey, modelName || null, id);
-      } else {
-        db.prepare(`
-          UPDATE provider_instances
-          SET name = ?, providerName = ?, modelName = ?
-          WHERE id = ?
-        `).run(name, providerName, modelName || null, id);
+      const target = db.prepare(`SELECT type FROM provider_instances WHERE id = ?`).get(id) as { type: string } | undefined;
+      if (target) {
+        db.prepare(`UPDATE provider_instances SET isActive = 0 WHERE type = ?`).run(target.type);
+        db.prepare(`UPDATE provider_instances SET isActive = 1 WHERE id = ?`).run(id);
       }
     } finally {
       db.close();
     }
   }
 
-  static getActive(): LLMProviderInstance | null {
+  static update(
+    id: string,
+    name: string,
+    providerName: string,
+    apiKey?: string,
+    modelName?: string,
+    type: "generative" | "embedding" = "generative"
+  ): void {
     const db = getSettingsDb();
     try {
-      // Query the DB
-      const row = db.prepare(`SELECT * FROM provider_instances WHERE isActive = 1`).get() as {
+      if (apiKey && apiKey.trim()) {
+        db.prepare(`
+          UPDATE provider_instances
+          SET name = ?, providerName = ?, apiKey = ?, modelName = ?, type = ?
+          WHERE id = ?
+        `).run(name, providerName, apiKey, modelName || null, type, id);
+      } else {
+        db.prepare(`
+          UPDATE provider_instances
+          SET name = ?, providerName = ?, modelName = ?, type = ?
+          WHERE id = ?
+        `).run(name, providerName, modelName || null, type, id);
+      }
+    } finally {
+      db.close();
+    }
+  }
+
+  static getActive(type: "generative" | "embedding" = "generative"): ModelProviderInstance | null {
+    const db = getSettingsDb();
+    try {
+      const row = db.prepare(`SELECT * FROM provider_instances WHERE isActive = 1 AND type = ?`).get(type) as {
         id: string;
         name: string;
         providerName: string;
         apiKey: string;
         isActive: number;
         modelName?: string;
+        type: string;
       } | undefined;
 
       if (!row) {
-        // Check if there are any rows at all
         const totalCount = db.prepare(`SELECT COUNT(*) as count FROM provider_instances`).get() as { count: number };
         if (totalCount.count === 0) {
-          // Database is completely empty! Check if GOOGLE_API_KEY env is set.
           const envKey = process.env.GOOGLE_API_KEY;
           if (envKey && envKey.trim()) {
-            // Auto-bootstrap default active instance from env
             const id = "provider-default-env";
             db.prepare(`
-              INSERT INTO provider_instances (id, name, providerName, apiKey, isActive, modelName)
-              VALUES (?, ?, ?, ?, ?, ?)
-            `).run(id, "Default (Env)", "google-genai", envKey, 1, "gemini-2.5-flash");
+              INSERT INTO provider_instances (id, name, providerName, apiKey, isActive, modelName, type)
+              VALUES (?, ?, ?, ?, ?, ?, ?)
+            `).run(id, "Default (Env)", "google-genai", envKey, 1, "gemini-2.5-flash", "generative");
+
+            const embedId = "provider-default-env-embed";
+            db.prepare(`
+              INSERT INTO provider_instances (id, name, providerName, apiKey, isActive, modelName, type)
+              VALUES (?, ?, ?, ?, ?, ?, ?)
+            `).run(embedId, "Default Embed (Env)", "google-genai", envKey, 1, "gemini-embedding-001", "embedding");
+
+            if (type === "embedding") {
+              return {
+                id: embedId,
+                name: "Default Embed (Env)",
+                providerName: "google-genai",
+                apiKey: envKey,
+                isActive: true,
+                modelName: "gemini-embedding-001",
+                type: "embedding",
+              };
+            }
 
             return {
               id,
@@ -173,6 +217,7 @@ export class ProviderManager {
               apiKey: envKey,
               isActive: true,
               modelName: "gemini-2.5-flash",
+              type: "generative",
             };
           }
         }
@@ -186,11 +231,22 @@ export class ProviderManager {
         apiKey: row.apiKey,
         isActive: true,
         modelName: row.modelName || undefined,
+        type: (row.type as "generative" | "embedding") || "generative",
       };
     } catch {
-      // Lock or write issue fallback: return an in-memory active key if env key exists
       const envKey = process.env.GOOGLE_API_KEY;
       if (envKey) {
+        if (type === "embedding") {
+          return {
+            id: "provider-default-env-embed-fallback",
+            name: "Default Embed (Env Fallback)",
+            providerName: "google-genai",
+            apiKey: envKey,
+            isActive: true,
+            modelName: "gemini-embedding-001",
+            type: "embedding",
+          };
+        }
         return {
           id: "provider-default-env-fallback",
           name: "Default (Env Fallback)",
@@ -198,6 +254,7 @@ export class ProviderManager {
           apiKey: envKey,
           isActive: true,
           modelName: "gemini-2.5-flash",
+          type: "generative",
         };
       }
       return null;

packages/llm/src/providers/google-genai.ts

@@ -1,10 +1,15 @@
 import { z } from "zod";
-import { ChatGoogleGenerativeAI } from "@langchain/google-genai";
-import { ILLMProvider, LLMRequest, LLMResponse, LLMCallRecord } from "../llm.js";
+import { ChatGoogleGenerativeAI, GoogleGenerativeAIEmbeddings } from "@langchain/google-genai";
+import { ILLMProvider, LLMRequest, LLMResponse, LLMCallRecord, IEmbeddingProvider } from "../llm.js";
 import { llmConfig } from "../config.js";
 import { ProviderManager } from "../provider-manager.js";
 
 export class GeminiProvider implements ILLMProvider {
+  static readonly providerId = "google-genai";
+  static readonly displayName = "Google Gemini";
+  static readonly description = "Official Gemini integration using Google Gen AI SDK";
+  static readonly defaultModel = "gemini-2.5-flash";
+
   providerName = "Gemini";
   private model: ChatGoogleGenerativeAI;
   lastCalls: LLMCallRecord[] = [];
@@ -14,7 +19,7 @@ export class GeminiProvider implements ILLMProvider {
     let model = modelName;
 
     if (!key) {
-      const active = ProviderManager.getActive();
+      const active = ProviderManager.getActive("generative");
       if (active) {
         key = active.apiKey;
         if (!model) {
@@ -73,3 +78,43 @@ export class GeminiProvider implements ILLMProvider {
     return { success: true, data: parsed, usage };
   }
 }
+
+export class GeminiEmbeddingProvider implements IEmbeddingProvider {
+  static readonly providerId = "google-genai";
+  static readonly displayName = "Google Gemini Embeddings";
+
+  providerName = "Gemini";
+  private model: GoogleGenerativeAIEmbeddings;
+
+  constructor(apiKey?: string, modelName?: string) {
+    let key = apiKey;
+    let model = modelName;
+
+    if (!key) {
+      const active = ProviderManager.getActive("embedding");
+      if (active) {
+        key = active.apiKey;
+        if (!model) {
+          model = active.modelName;
+        }
+      }
+    }
+
+    if (!key) {
+      key = llmConfig.GOOGLE_API_KEY;
+    }
+
+    if (!key) {
+      throw new Error("GOOGLE_API_KEY is required to initialize GeminiEmbeddingProvider");
+    }
+
+    this.model = new GoogleGenerativeAIEmbeddings({
+      apiKey: key,
+      modelName: model || "gemini-embedding-001",
+    });
+  }
+
+  async embed(text: string): Promise<number[]> {
+    return this.model.embedQuery(text);
+  }
+}

packages/llm/src/providers/mock.ts

@@ -1,7 +1,12 @@
 import { z } from "zod";
-import { ILLMProvider, LLMRequest, LLMResponse, LLMCallRecord } from "../llm.js";
+import { ILLMProvider, LLMRequest, LLMResponse, LLMCallRecord, IEmbeddingProvider } from "../llm.js";
 
 export class MockLLMProvider implements ILLMProvider {
+  static readonly providerId = "mock";
+  static readonly displayName = "Mock LLM Provider";
+  static readonly description = "Stateless mock provider for testing and offline development";
+  static readonly defaultModel = "mock";
+
   providerName = "mock";
   private callCount = 0;
   lastCalls: LLMCallRecord[] = [];
@@ -29,3 +34,21 @@ export class MockLLMProvider implements ILLMProvider {
     }
   }
 }
+
+export class MockEmbeddingProvider implements IEmbeddingProvider {
+  static readonly providerId = "mock";
+
+  providerName = "mock";
+
+  constructor(private modelName?: string) {}
+
+  async embed(text: string): Promise<number[]> {
+    // Return a deterministic mock 768-dimensional vector based on the text
+    const vec = new Array(768).fill(0).map((_, i) => {
+      // Return a predictable float between -1.0 and 1.0
+      const charCode = text.charCodeAt(i % text.length) || 0;
+      return Math.sin(charCode + i);
+    });
+    return vec;
+  }
+}

packages/llm/src/providers/openrouter.ts

@@ -0,0 +1,80 @@
+import { z } from "zod";
+import { ChatOpenRouter } from "@langchain/openrouter";
+import { ILLMProvider, LLMRequest, LLMResponse, LLMCallRecord } from "../llm.js";
+import { llmConfig } from "../config.js";
+import { ProviderManager } from "../provider-manager.js";
+
+export class OpenRouterProvider implements ILLMProvider {
+  static readonly providerId = "openrouter";
+  static readonly displayName = "OpenRouter";
+  static readonly description = "Multi-model router supporting Anthropic, OpenAI, DeepSeek, and local models";
+  static readonly defaultModel = "google/gemini-2.5-flash";
+
+  providerName = "OpenRouter";
+  private model: ChatOpenRouter;
+  lastCalls: LLMCallRecord[] = [];
+
+  constructor(apiKey?: string, modelName?: string) {
+    let key = apiKey;
+    let model = modelName;
+
+    if (!key) {
+      const active = ProviderManager.getActive("generative");
+      if (active) {
+        key = active.apiKey;
+        if (!model) {
+          model = active.modelName;
+        }
+      }
+    }
+
+    if (!key) {
+      key = llmConfig.OPENROUTER_API_KEY;
+    }
+
+    if (!key) {
+      throw new Error("OPENROUTER_API_KEY is required to initialize OpenRouterProvider");
+    }
+
+    this.model = new ChatOpenRouter({
+      apiKey: key,
+      model: model || "google/gemini-2.5-flash",
+    });
+  }
+
+  async generateStructuredResponse<T extends z.ZodTypeAny>(
+    request: LLMRequest<T>,
+  ): Promise<LLMResponse<z.infer<T>>> {
+    const structuredModel = this.model.withStructuredOutput(request.schema, { includeRaw: true });
+    const result = (await structuredModel.invoke([
+      { role: "system", content: request.systemPrompt },
+      { role: "user", content: request.userContext },
+    ])) as unknown as {
+      parsed?: z.infer<T>;
+      raw?: {
+        usage_metadata?: {
+          input_tokens?: number;
+          output_tokens?: number;
+          total_tokens?: number;
+        };
+      };
+    };
+
+    const parsed = result?.parsed;
+    const raw = result?.raw;
+
+    const usage = raw?.usage_metadata ? {
+      inputTokens: raw.usage_metadata.input_tokens || 0,
+      outputTokens: raw.usage_metadata.output_tokens || 0,
+      totalTokens: raw.usage_metadata.total_tokens || 0,
+    } : undefined;
+
+    this.lastCalls.push({
+      systemPrompt: request.systemPrompt,
+      userContext: request.userContext,
+      usage,
+    });
+
+    return { success: true, data: parsed, usage };
+  }
+}

packages/llm/tests/mock.test.ts

@@ -1,6 +1,6 @@
 import { describe, test, expect } from "vitest";
 import { z } from "zod";
-import { MockLLMProvider } from "@omnia/llm";
+import { MockLLMProvider, MockEmbeddingProvider } from "@omnia/llm";
 
 describe("MockLLMProvider Unit Tests (Tier 1)", () => {
   test("returns parsed matching data for valid mock response", async () => {
@@ -61,3 +61,21 @@ describe("MockLLMProvider Unit Tests (Tier 1)", () => {
     expect(response.data).toBeUndefined();
   });
 });
+
+describe("MockEmbeddingProvider Unit Tests (Tier 1)", () => {
+  test("generates deterministic 768-dimensional vectors", async () => {
+    const provider = new MockEmbeddingProvider("mock-embeddings");
+    const text = "Hello world";
+    const vec1 = await provider.embed(text);
+    const vec2 = await provider.embed(text);
+
+    expect(vec1.length).toBe(768);
+    expect(vec2.length).toBe(768);
+    expect(vec1).toEqual(vec2); // Deterministic
+    
+    // Ensure values are numbers between -1.0 and 1.0 (since they are generated with Math.sin)
+    expect(typeof vec1[0]).toBe("number");
+    expect(vec1[0]).toBeGreaterThanOrEqual(-1.0);
+    expect(vec1[0]).toBeLessThanOrEqual(1.0);
+  });
+});

packages/llm/tests/openrouter.test.ts

@@ -0,0 +1,107 @@
+import { describe, test, expect, vi } from "vitest";
+import { z } from "zod";
+import { OpenRouterProvider } from "../src/providers/openrouter.js";
+import { llmConfig } from "../src/config.js";
+
+// Mock the ChatOpenRouter class
+vi.mock("@langchain/openrouter", () => {
+  return {
+    ChatOpenRouter: class {
+      config: unknown;
+      constructor(config: unknown) {
+        this.config = config;
+      }
+      withStructuredOutput = vi.fn().mockImplementation(() => {
+        return {
+          invoke: vi.fn().mockImplementation(async () => {
+            // Return a mock output that matches the includeRaw: true structure
+            return {
+              parsed: {
+                name: "mocked response",
+                success: true,
+              },
+              raw: {
+                usage_metadata: {
+                  input_tokens: 10,
+                  output_tokens: 5,
+                  total_tokens: 15,
+                },
+              },
+            };
+          }),
+        };
+      });
+    },
+  };
+});
+
+describe("OpenRouterProvider Unit Tests (Tier 1)", () => {
+  test("initializes successfully with a provided apiKey", () => {
+    const provider = new OpenRouterProvider("dummy-key");
+    expect(provider.providerName).toBe("OpenRouter");
+  });
+
+  test("initializes successfully with apiKey from config", () => {
+    // Save current config
+    const originalKey = llmConfig.OPENROUTER_API_KEY;
+    llmConfig.OPENROUTER_API_KEY = "env-dummy-key";
+    
+    try {
+      const provider = new OpenRouterProvider();
+      expect(provider.providerName).toBe("OpenRouter");
+    } finally {
+      llmConfig.OPENROUTER_API_KEY = originalKey;
+    }
+  });
+
+  test("throws error if no API key is provided or in config", () => {
+    // Save current config
+    const originalKey = llmConfig.OPENROUTER_API_KEY;
+    llmConfig.OPENROUTER_API_KEY = undefined;
+
+    try {
+      expect(() => new OpenRouterProvider()).toThrow(
+        "OPENROUTER_API_KEY is required to initialize OpenRouterProvider"
+      );
+    } finally {
+      llmConfig.OPENROUTER_API_KEY = originalKey;
+    }
+  });
+
+  test("generateStructuredResponse invokes the model with structured output, records usage and updates lastCalls", async () => {
+    const provider = new OpenRouterProvider("dummy-key");
+    const TestSchema = z.object({
+      name: z.string(),
+      success: z.boolean(),
+    });
+
+    const response = await provider.generateStructuredResponse({
+      systemPrompt: "system prompt",
+      userContext: "user context",
+      schema: TestSchema,
+    });
+
+    expect(response.success).toBe(true);
+    expect(response.data).toEqual({
+      name: "mocked response",
+      success: true,
+    });
+
+    expect(response.usage).toEqual({
+      inputTokens: 10,
+      outputTokens: 5,
+      totalTokens: 15,
+    });
+
+    expect(provider.lastCalls.length).toBe(1);
+    expect(provider.lastCalls[0]).toEqual({
+      systemPrompt: "system prompt",
+      userContext: "user context",
+      usage: {
+        inputTokens: 10,
+        outputTokens: 5,
+        totalTokens: 15,
+      },
+    });
+  });
+});

packages/memory/src/index.ts

@@ -1 +1,2 @@
 export * from "./buffer.js";
+export * from "./ledger.js";

packages/memory/src/ledger.ts

@@ -0,0 +1,379 @@
+import Database from "better-sqlite3";
+
+export interface LedgerEntry {
+  id: string;
+  ownerId: string;
+  timestamp: string;
+  locationId: string | null;
+  involvedEntityIds: string[];
+
+  content: string;
+  quotes: string[];
+  importance: number;
+  embedding: number[];
+}
+
+export class LedgerRepository {
+  constructor(private db: Database.Database) {
+    // Enable foreign keys for cascading deletes
+    this.db.exec("PRAGMA foreign_keys = ON;");
+    this.initializeSchema();
+  }
+
+  private initializeSchema(): void {
+    this.db.exec(`
+      CREATE TABLE IF NOT EXISTS ledger_entries (
+        id TEXT PRIMARY KEY,
+        owner_id TEXT NOT NULL,
+        timestamp TEXT NOT NULL,
+        location_id TEXT,
+        content TEXT NOT NULL,
+        quotes_json TEXT,
+        importance INTEGER NOT NULL,
+        embedding BLOB,
+        FOREIGN KEY (owner_id) REFERENCES objects(id) ON DELETE CASCADE
+      );
+
+      CREATE TABLE IF NOT EXISTS ledger_involved_entities (
+        entry_id TEXT NOT NULL,
+        entity_id TEXT NOT NULL,
+        PRIMARY KEY (entry_id, entity_id),
+        FOREIGN KEY (entry_id) REFERENCES ledger_entries(id) ON DELETE CASCADE
+      );
+
+      CREATE INDEX IF NOT EXISTS idx_ledger_owner ON ledger_entries(owner_id);
+      CREATE INDEX IF NOT EXISTS idx_ledger_location ON ledger_entries(location_id);
+      CREATE INDEX IF NOT EXISTS idx_ledger_importance ON ledger_entries(importance);
+      CREATE INDEX IF NOT EXISTS idx_ledger_involved_entity ON ledger_involved_entities(entity_id);
+    `);
+  }
+
+  save(entry: LedgerEntry): void {
+    const insertEntry = this.db.prepare(`
+      INSERT INTO ledger_entries (id, owner_id, timestamp, location_id, content, quotes_json, importance, embedding)
+      VALUES (?, ?, ?, ?, ?, ?, ?, ?)
+      ON CONFLICT(id) DO UPDATE SET
+        owner_id = excluded.owner_id,
+        timestamp = excluded.timestamp,
+        location_id = excluded.location_id,
+        content = excluded.content,
+        quotes_json = excluded.quotes_json,
+        importance = excluded.importance,
+        embedding = excluded.embedding
+    `);
+
+    const insertEntity = this.db.prepare(`
+      INSERT OR IGNORE INTO ledger_involved_entities (entry_id, entity_id)
+      VALUES (?, ?)
+    `);
+
+    const deleteEntities = this.db.prepare(`
+      DELETE FROM ledger_involved_entities WHERE entry_id = ?
+    `);
+
+    this.db.transaction(() => {
+      insertEntry.run(
+        entry.id,
+        entry.ownerId,
+        entry.timestamp,
+        entry.locationId,
+        entry.content,
+        JSON.stringify(entry.quotes),
+        entry.importance,
+        entry.embedding.length > 0
+          ? Buffer.from(new Float32Array(entry.embedding).buffer)
+          : null
+      );
+
+      deleteEntities.run(entry.id);
+      for (const entityId of entry.involvedEntityIds) {
+        insertEntity.run(entry.id, entityId);
+      }
+    })();
+  }
+
+  private mapRowToEntry(row: any, involvedEntityIds: string[]): LedgerEntry {
+    let embedding: number[] = [];
+    if (row.embedding) {
+      const buffer = row.embedding as Buffer;
+      const floatArray = new Float32Array(
+        buffer.buffer,
+        buffer.byteOffset,
+        buffer.byteLength / Float32Array.BYTES_PER_ELEMENT
+      );
+      embedding = Array.from(floatArray);
+    }
+
+    return {
+      id: row.id,
+      ownerId: row.owner_id,
+      timestamp: row.timestamp,
+      locationId: row.location_id,
+      involvedEntityIds,
+      content: row.content,
+      quotes: JSON.parse(row.quotes_json || "[]"),
+      importance: row.importance,
+      embedding: embedding,
+    };
+  }
+
+  load(id: string): LedgerEntry | null {
+    const row = this.db
+      .prepare(
+        `
+      SELECT id, owner_id, timestamp, location_id, content, quotes_json, importance, embedding
+      FROM ledger_entries
+      WHERE id = ?
+    `
+      )
+      .get(id) as any;
+
+    if (!row) return null;
+
+    const entitiesRows = this.db
+      .prepare(
+        `
+      SELECT entity_id FROM ledger_involved_entities WHERE entry_id = ?
+    `
+      )
+      .all(id) as { entity_id: string }[];
+
+    return this.mapRowToEntry(row, entitiesRows.map((er) => er.entity_id));
+  }
+
+  /**
+   * Retrieves relevant ledger entries using Phase 1: Deterministic Heuristic Filtering
+   * Filters by:
+   * 1. locationId matches current location
+   * 2. involvedEntityIds overlaps with current involved entities
+   * 3. importance >= 8 (high salience)
+   */
+  getRelevant(
+    ownerId: string,
+    currentLocationId: string | null,
+    currentInvolvedEntityIds: string[],
+    limit: number = 20
+  ): LedgerEntry[] {
+    let query = `
+      SELECT DISTINCT le.id, le.owner_id, le.timestamp, le.location_id, le.content, le.quotes_json, le.importance, le.embedding
+      FROM ledger_entries le
+      LEFT JOIN ledger_involved_entities lie ON le.id = lie.entry_id
+      WHERE le.owner_id = ? 
+        AND (
+          le.importance >= 8
+    `;
+
+    const params: any[] = [ownerId];
+
+    if (currentLocationId) {
+      query += ` OR le.location_id = ?`;
+      params.push(currentLocationId);
+    }
+
+    if (currentInvolvedEntityIds.length > 0) {
+      const placeholders = currentInvolvedEntityIds.map(() => "?").join(",");
+      query += ` OR lie.entity_id IN (${placeholders})`;
+      params.push(...currentInvolvedEntityIds);
+    }
+
+    query += `
+        )
+      ORDER BY le.timestamp DESC
+      LIMIT ?
+    `;
+    params.push(limit);
+
+    const rows = this.db.prepare(query).all(...params) as any[];
+
+    if (rows.length === 0) return [];
+
+    const entryIds = rows.map((r) => r.id);
+    const placeholders = entryIds.map(() => "?").join(",");
+    const entitiesRows = this.db
+      .prepare(
+        `
+      SELECT entry_id, entity_id FROM ledger_involved_entities
+      WHERE entry_id IN (${placeholders})
+    `
+      )
+      .all(...entryIds) as { entry_id: string; entity_id: string }[];
+
+    const entitiesMap = new Map<string, string[]>();
+    for (const er of entitiesRows) {
+      if (!entitiesMap.has(er.entry_id)) {
+        entitiesMap.set(er.entry_id, []);
+      }
+      entitiesMap.get(er.entry_id)!.push(er.entity_id);
+    }
+
+    return rows.map((row) => this.mapRowToEntry(row, entitiesMap.get(row.id) || []));
+  }
+
+  private fetchRawNeighbors(ownerId: string, timestamp: string): LedgerEntry[] {
+    const neighbors: LedgerEntry[] = [];
+
+    // Preceding entry
+    const preceding = this.db
+      .prepare(
+        `
+      SELECT id, owner_id, timestamp, location_id, content, quotes_json, importance, embedding
+      FROM ledger_entries
+      WHERE owner_id = ? AND timestamp < ?
+      ORDER BY timestamp DESC
+      LIMIT 1
+    `
+      )
+      .get(ownerId, timestamp) as any;
+
+    if (preceding) {
+      neighbors.push(this.mapRowToEntry(preceding, []));
+    }
+
+    // Succeeding entry
+    const succeeding = this.db
+      .prepare(
+        `
+      SELECT id, owner_id, timestamp, location_id, content, quotes_json, importance, embedding
+      FROM ledger_entries
+      WHERE owner_id = ? AND timestamp > ?
+      ORDER BY timestamp ASC
+      LIMIT 1
+    `
+      )
+      .get(ownerId, timestamp) as any;
+
+    if (succeeding) {
+      neighbors.push(this.mapRowToEntry(succeeding, []));
+    }
+
+    return neighbors;
+  }
+
+  /**
+   * Phase 1 + Phase 2 Retrieval Pipeline
+   * 1. Fetches candidates via Phase 1 heuristic filtering.
+   * 2. Ranks them using: Score = Recency + Importance + Semantic Match.
+   * 3. Selects the top `limit` memories.
+   * 4. Optionally pulls in the immediate chronological neighbors (associative chain).
+   * 5. Returns all gathered entries sorted chronologically (timestamp ASC).
+   */
+  retrieve(
+    ownerId: string,
+    currentLocationId: string | null,
+    currentInvolvedEntityIds: string[],
+    queryEmbedding?: number[],
+    now: Date = new Date(),
+    limit: number = 5,
+    options?: {
+      includeAssociativeNeighbors?: boolean;
+      recencyWeight?: number;
+      importanceWeight?: number;
+      relevanceWeight?: number;
+      decayRate?: number;
+    }
+  ): LedgerEntry[] {
+    const includeAssociativeNeighbors = options?.includeAssociativeNeighbors ?? false;
+    const recencyWeight = options?.recencyWeight ?? 1.0;
+    const importanceWeight = options?.importanceWeight ?? 1.0;
+    const relevanceWeight = options?.relevanceWeight ?? 1.0;
+    const decayRate = options?.decayRate ?? 0.99;
+
+    // Fetch candidate pool (limit 100 to provide enough options for Phase 2 ranking)
+    const candidates = this.getRelevant(ownerId, currentLocationId, currentInvolvedEntityIds, 100);
+    if (candidates.length === 0) return [];
+
+    // Score candidates
+    const scored = candidates.map((entry) => {
+      // Recency calculation with exponential decay
+      const deltaMs = now.getTime() - new Date(entry.timestamp).getTime();
+      const hoursElapsed = Math.max(0, deltaMs / (3600 * 1000));
+      const recency = Math.pow(decayRate, hoursElapsed);
+
+      // Importance score normalized (0.0 to 1.0)
+      const importanceNorm = entry.importance / 10.0;
+
+      // Semantic relevance
+      let relevance = 0;
+      if (queryEmbedding && entry.embedding && entry.embedding.length > 0) {
+        relevance = cosineSimilarity(queryEmbedding, entry.embedding);
+      }
+
+      const score =
+        recencyWeight * recency +
+        importanceWeight * importanceNorm +
+        relevanceWeight * relevance;
+
+      return { entry, score };
+    });
+
+    // Rank and take top memories
+    scored.sort((a, b) => b.score - a.score);
+    const selected = scored.slice(0, limit).map((s) => s.entry);
+
+    let finalEntries = [...selected];
+
+    // Optionally retrieve associative neighbors
+    if (includeAssociativeNeighbors && selected.length > 0) {
+      const neighborMap = new Map<string, LedgerEntry>();
+
+      for (const entry of selected) {
+        const rawNeighbors = this.fetchRawNeighbors(ownerId, entry.timestamp);
+        for (const rn of rawNeighbors) {
+          if (!finalEntries.some((fe) => fe.id === rn.id) && !neighborMap.has(rn.id)) {
+            neighborMap.set(rn.id, rn);
+          }
+        }
+      }
+
+      const neighborsToPopulate = Array.from(neighborMap.values());
+      if (neighborsToPopulate.length > 0) {
+        const neighborIds = neighborsToPopulate.map((n) => n.id);
+        const placeholders = neighborIds.map(() => "?").join(",");
+        const entitiesRows = this.db
+          .prepare(
+            `
+          SELECT entry_id, entity_id FROM ledger_involved_entities
+          WHERE entry_id IN (${placeholders})
+        `
+          )
+          .all(...neighborIds) as { entry_id: string; entity_id: string }[];
+
+        const entitiesMap = new Map<string, string[]>();
+        for (const er of entitiesRows) {
+          if (!entitiesMap.has(er.entry_id)) {
+            entitiesMap.set(er.entry_id, []);
+          }
+          entitiesMap.get(er.entry_id)!.push(er.entity_id);
+        }
+
+        for (const n of neighborsToPopulate) {
+          n.involvedEntityIds = entitiesMap.get(n.id) || [];
+          finalEntries.push(n);
+        }
+      }
+    }
+
+    // Sort chronologically ASC for the final prompt output
+    finalEntries.sort((a, b) => new Date(a.timestamp).getTime() - new Date(b.timestamp).getTime());
+
+    return finalEntries;
+  }
+
+  delete(id: string): void {
+    this.db.prepare(`DELETE FROM ledger_entries WHERE id = ?`).run(id);
+  }
+}
+
+function cosineSimilarity(a: number[], b: number[]): number {
+  if (a.length !== b.length || a.length === 0) return 0;
+  let dot = 0;
+  let normA = 0;
+  let normB = 0;
+  for (let i = 0; i < a.length; i++) {
+    dot += a[i] * b[i];
+    normA += a[i] * a[i];
+    normB += b[i] * b[i];
+  }
+  if (normA === 0 || normB === 0) return 0;
+  return dot / (Math.sqrt(normA) * Math.sqrt(normB));
+}

packages/memory/tests/ledger.test.ts

@@ -0,0 +1,228 @@
+import { describe, it, expect, beforeEach, afterEach } from "vitest";
+import Database from "better-sqlite3";
+import { LedgerRepository, LedgerEntry } from "../src/ledger";
+
+describe("LedgerRepository", () => {
+  let db: Database.Database;
+  let repo: LedgerRepository;
+
+  beforeEach(() => {
+    db = new Database(":memory:");
+    
+    // We need to create a dummy objects table to satisfy foreign keys
+    db.exec(`
+      CREATE TABLE objects (
+        id TEXT PRIMARY KEY
+      );
+    `);
+
+    db.exec(`
+      INSERT INTO objects (id) VALUES ('alice'), ('bob'), ('charlie');
+    `);
+
+    repo = new LedgerRepository(db);
+  });
+
+  afterEach(() => {
+    db.close();
+  });
+
+  it("should save and load a ledger entry", () => {
+    const entry: LedgerEntry = {
+      id: "mem1",
+      ownerId: "alice",
+      timestamp: new Date().toISOString(),
+      locationId: "loc1",
+      involvedEntityIds: ["bob", "charlie"],
+      content: "Alice met Bob and Charlie at the market.",
+      quotes: ["Hi guys!"],
+      importance: 5,
+      embedding: [0.1, 0.2, 0.3],
+    };
+
+    repo.save(entry);
+
+    const loaded = repo.load("mem1");
+    expect(loaded).toBeDefined();
+    expect(loaded?.id).toBe("mem1");
+    expect(loaded?.ownerId).toBe("alice");
+    expect(loaded?.locationId).toBe("loc1");
+    expect(loaded?.involvedEntityIds.sort()).toEqual(["bob", "charlie"].sort());
+    expect(loaded?.content).toBe(entry.content);
+    expect(loaded?.quotes).toEqual(entry.quotes);
+    expect(loaded?.importance).toBe(5);
+    
+    // Check float precision
+    expect(loaded?.embedding[0]).toBeCloseTo(0.1);
+    expect(loaded?.embedding[1]).toBeCloseTo(0.2);
+    expect(loaded?.embedding[2]).toBeCloseTo(0.3);
+  });
+
+  it("should return null for non-existent entry", () => {
+    const loaded = repo.load("missing");
+    expect(loaded).toBeNull();
+  });
+
+  it("should retrieve relevant memories based on Phase 1 heuristics", () => {
+    repo.save({
+      id: "mem_high_salience",
+      ownerId: "alice",
+      timestamp: "2024-01-01T10:00:00.000Z",
+      locationId: "loc2",
+      involvedEntityIds: [],
+      content: "Alice found a magical sword.",
+      quotes: [],
+      importance: 9, // high salience
+      embedding: [],
+    });
+
+    repo.save({
+      id: "mem_location",
+      ownerId: "alice",
+      timestamp: "2024-01-02T10:00:00.000Z",
+      locationId: "loc1", // matches query
+      involvedEntityIds: [],
+      content: "Alice sat on a bench.",
+      quotes: [],
+      importance: 2,
+      embedding: [],
+    });
+
+    repo.save({
+      id: "mem_social",
+      ownerId: "alice",
+      timestamp: "2024-01-03T10:00:00.000Z",
+      locationId: "loc2",
+      involvedEntityIds: ["bob"], // matches query
+      content: "Alice waved at Bob.",
+      quotes: [],
+      importance: 3,
+      embedding: [],
+    });
+
+    repo.save({
+      id: "mem_irrelevant",
+      ownerId: "alice",
+      timestamp: "2024-01-04T10:00:00.000Z",
+      locationId: "loc3",
+      involvedEntityIds: ["charlie"],
+      content: "Alice sneezed.",
+      quotes: [],
+      importance: 2,
+      embedding: [],
+    });
+
+    const relevant = repo.getRelevant("alice", "loc1", ["bob"]);
+    
+    expect(relevant).toHaveLength(3);
+    const ids = relevant.map((r) => r.id);
+    expect(ids).toContain("mem_high_salience"); // due to importance >= 8
+    expect(ids).toContain("mem_location"); // due to locationId
+    expect(ids).toContain("mem_social"); // due to involvedEntityIds
+    expect(ids).not.toContain("mem_irrelevant");
+  });
+
+  it("should retrieve ranked memories with recency, importance, and semantic match", () => {
+    const now = new Date("2024-01-10T12:00:00.000Z");
+
+    repo.save({
+      id: "mem1",
+      ownerId: "alice",
+      timestamp: "2024-01-01T12:00:00.000Z",
+      locationId: "loc1",
+      involvedEntityIds: [],
+      content: "Alice fought a dragon.",
+      quotes: [],
+      importance: 10,
+      embedding: [0, 1, 0],
+    });
+
+    repo.save({
+      id: "mem2",
+      ownerId: "alice",
+      timestamp: "2024-01-10T11:00:00.000Z",
+      locationId: "loc1",
+      involvedEntityIds: [],
+      content: "Alice ate a sandwich.",
+      quotes: [],
+      importance: 2,
+      embedding: [1, 0, 0],
+    });
+
+    repo.save({
+      id: "mem3",
+      ownerId: "alice",
+      timestamp: "2024-01-10T11:50:00.000Z",
+      locationId: "loc1",
+      involvedEntityIds: [],
+      content: "Alice read a book.",
+      quotes: [],
+      importance: 5,
+      embedding: [0.707, 0.707, 0],
+    });
+
+    // Query: [1, 0, 0]
+    // mem3 score: recency (~0.998) + importance (0.5) + relevance (0.707) = ~2.205
+    // mem2 score: recency (~0.99) + importance (0.2) + relevance (1.0) = ~2.19
+    // mem1 score: recency (~0.114) + importance (1.0) + relevance (0.0) = ~1.114
+    // If limit = 2, should return mem2 and mem3, sorted chronologically (mem2 first, then mem3)
+    const results = repo.retrieve("alice", "loc1", [], [1, 0, 0], now, 2);
+    expect(results).toHaveLength(2);
+    expect(results[0].id).toBe("mem2");
+    expect(results[1].id).toBe("mem3");
+  });
+
+  it("should pull in associative neighbors when specified", () => {
+    repo.save({
+      id: "mem_preceding",
+      ownerId: "alice",
+      timestamp: "2024-01-10T10:00:00.000Z",
+      locationId: "loc_other",
+      involvedEntityIds: [],
+      content: "Alice woke up.",
+      quotes: [],
+      importance: 2,
+      embedding: [],
+    });
+
+    repo.save({
+      id: "mem_target",
+      ownerId: "alice",
+      timestamp: "2024-01-10T11:00:00.000Z",
+      locationId: "loc1",
+      involvedEntityIds: [],
+      content: "Alice arrived at tavern.",
+      quotes: [],
+      importance: 2,
+      embedding: [],
+    });
+
+    repo.save({
+      id: "mem_succeeding",
+      ownerId: "alice",
+      timestamp: "2024-01-10T12:00:00.000Z",
+      locationId: "loc_other",
+      involvedEntityIds: [],
+      content: "Alice ordered ale.",
+      quotes: [],
+      importance: 2,
+      embedding: [],
+    });
+
+    // Without neighbors: only returns mem_target
+    const withoutNeighbors = repo.retrieve("alice", "loc1", [], undefined, new Date("2024-01-10T14:00:00.000Z"), 1, {
+      includeAssociativeNeighbors: false,
+    });
+    expect(withoutNeighbors).toHaveLength(1);
+    expect(withoutNeighbors[0].id).toBe("mem_target");
+
+    // With neighbors: returns preceding, target, and succeeding sorted chronologically
+    const withNeighbors = repo.retrieve("alice", "loc1", [], undefined, new Date("2024-01-10T14:00:00.000Z"), 1, {
+      includeAssociativeNeighbors: true,
+    });
+    expect(withNeighbors).toHaveLength(3);
+    expect(withNeighbors[0].id).toBe("mem_preceding");
+    expect(withNeighbors[1].id).toBe("mem_target");
+    expect(withNeighbors[2].id).toBe("mem_succeeding");
+  });
+});

pnpm-workspace.yaml

@@ -8,6 +8,7 @@ allowBuilds:
   esbuild: true
   sharp: true
   unrs-resolver: true
+  workerd: true
 minimumReleaseAgeExclude:
   - '@astrojs/telemetry@3.3.3'
   - astro@7.0.7

web/docs/astro.config.mjs

@@ -5,10 +5,12 @@ import mermaid from "astro-mermaid";
 export default defineConfig({
   site: "https://omnia.omniasimulation.com",
   base: "/docs",
+  outDir: "./dist/docs",
   integrations: [
     mermaid(),
     starlight({
       title: "Omnia Docs",
+      favicon: "/favicon.png",
       logo: {
         src: "./src/assets/img/logo.png",
         replacesTitle: true,

web/docs/package.json

@@ -7,11 +7,17 @@
     "dev": "astro dev",
     "start": "astro dev",
     "build": "astro build",
-    "preview": "astro preview"
+    "preview": "astro preview",
+    "preview:wrangler": "astro build && wrangler dev"
   },
   "dependencies": {
     "@astrojs/starlight": "^0.41.3",
     "astro": "^7.0.7",
+    "astro-mermaid": "^2.1.0",
+    "mermaid": "^11.16.0",
     "sharp": "^0.33.5"
+  },
+  "devDependencies": {
+    "wrangler": "^4.107.1"
   }
 }

web/docs/src/content/docs/architecture/llm-providers.md

@@ -21,9 +21,10 @@ export interface ILLMProvider {
 }
 ```
 
-The codebase provides two primary implementations:
+The codebase provides three primary implementations:
 1. **`GeminiProvider`:** The production provider utilizing Google's Gemini Models via the `@langchain/google-genai` SDK.
-2. **`MockLLMProvider`:** A stateless, pre-programmed mock provider used for fast, deterministic unit testing and local integration tests.
+2. **`OpenRouterProvider`:** The production provider utilizing OpenRouter via the `@langchain/openrouter` SDK, allowing routing through various third-party and local models.
+3. **`MockLLMProvider`:** A stateless, pre-programmed mock provider used for fast, deterministic unit testing and local integration tests.
 
 ---
 
@@ -43,10 +44,10 @@ export interface LLMProviderInstance {
 ```
 
 Users can register multiple provider instances in the **Configuration Page** under the GUI. Each instance is given:
-* A friendly, human-readable name (e.g., `"Gemini Production Key"`, `"Experimental Gemini Pro"`).
-* A provider type (e.g., `google-genai`, `mock`).
+* A friendly, human-readable name (e.g., `"Gemini Production Key"`, `"OpenRouter Claude Key"`).
+* A provider type (e.g., `google-genai`, `openrouter`, `mock`).
 * An API key credential.
-* A custom target model name (e.g., `gemini-2.5-flash` or `gemini-2.5-pro`).
+* A custom target model name (e.g., `gemini-2.5-flash`, `anthropic/claude-3-5-sonnet`, or local model paths).
 * An **Active** status flag (one key is marked as globally active).
 
 Configurations are stored globally in `data/settings.db` (separated from specific simulation run databases like `data/sim-*.db` to keep key storage and audit logs isolated).
@@ -59,10 +60,10 @@ During a simulation run, the engine executes four distinct LLM operations. To op
 
 | Task Name | Key ID | Description | Default Model |
 | :--- | :--- | :--- | :--- |
-| **Actor Prose Generation** | `actor-prose` | Generates roleplay and narrative behavioral prose for Non-Player Characters. | `gemini-2.5-flash` |
-| **LLM Validator** | `llm-validator` | Arbitrates and validates proposed actions against the world state rules and constraints. | `gemini-2.5-flash` |
-| **Intent Decoder** | `intent-decoder` | Parses and splits free-text actions/prose into structured intent sequences. | `gemini-2.5-flash` |
-| **TimeDelta Generator** | `timedelta` | Calculates the duration of character actions to advance the game clock. | `gemini-2.5-flash` |
+| **Actor Prose Generation** | `actor-prose` | Generates roleplay and narrative behavioral prose for Non-Player Characters. | `gemini-2.5-flash` / `google/gemini-2.5-flash` |
+| **LLM Validator** | `llm-validator` | Arbitrates and validates proposed actions against the world state rules and constraints. | `gemini-2.5-flash` / `google/gemini-2.5-flash` |
+| **Intent Decoder** | `intent-decoder` | Parses and splits free-text actions/prose into structured intent sequences. | `gemini-2.5-flash` / `google/gemini-2.5-flash` |
+| **TimeDelta Generator** | `timedelta` | Calculates the duration of character actions to advance the game clock. | `gemini-2.5-flash` / `google/gemini-2.5-flash` |
 
 If no specific provider instance is mapped to a task, the task automatically routes to the globally marked **Active** provider instance.
 
@@ -72,7 +73,7 @@ If no specific provider instance is mapped to a task, the task automatically rou
 
 To maintain backwards-compatibility and support headless runs, live evaluation suites, and automated unit tests without requiring database pre-configuration, the config manager supports **self-bootstrapping**:
 
-1. When the provider manager queries the active key instance, if `data/settings.db` contains **0 registered keys**, it checks the process environment for `GOOGLE_API_KEY`.
+1. When the provider manager queries the active key instance, if `data/settings.db` contains **0 registered keys**, it checks the process environment for `GOOGLE_API_KEY` or `OPENROUTER_API_KEY`.
 2. If `process.env.GOOGLE_API_KEY` is present, it automatically creates, saves, and activates a default provider instance (`Default (Env)`) in `settings.db`.
 3. If database write locks occur (e.g., during high-concurrency Vitest test suites), the system seamlessly returns a temporary in-memory `LLMProviderInstance` to keep execution fluent and error-free.
 

web/docs/src/content/docs/architecture/memory-tier2.md

@@ -0,0 +1,115 @@
+---
+title: Tier 2 Memory (Ledger)
+description: Long-term episodic memory storage and retrieval
+---
+
+Tier 2 memory lives in between the memory buffer and tier 3 dossiers and arguably takes up the largest share of the context pie.
+
+Tier 2 memory (or long-term memory) stores historical events that happened to the entity in the past. It acts as an episodic ledger.
+
+```ts
+interface LedgerEntry {
+  id: string;
+  ownerId: string; // whose subjective memory this belongs to
+  timestamp: string; // ISO, tied to WorldClock when the intent causing the event happened.
+  locationId: string | null; // where it happened
+  involvedEntityIds: string[]; // who else this event concerns
+
+  content: string; // third-person narrative summary — recallable
+  quotes: string[]; // verbatim lines, only for high-salience dialogue
+  importance: number; // 1–10, salience assigned at handoff
+  embedding: number[]; // for semantic search (storage representation TBD at build time)
+}
+```
+
+### Storage Model
+
+Tier 2 memory is stored in relational tables to allow efficient deterministic filtering. Embeddings are stored as raw BLOBs (containing a serialized `Float32Array`). 
+
+To avoid the build and installation friction associated with native C-extensions like `sqlite-vec` (e.g. node-gyp issues across platforms), index optimization relies on standard SQLite secondary indices. These indices allow database queries to execute in microseconds, even with hundreds of thousands of memories:
+
+```sql
+CREATE TABLE IF NOT EXISTS ledger_entries (
+  id TEXT PRIMARY KEY,
+  owner_id TEXT NOT NULL,
+  timestamp TEXT NOT NULL,
+  location_id TEXT,
+  content TEXT NOT NULL,
+  quotes_json TEXT,
+  importance INTEGER NOT NULL,
+  embedding BLOB,
+  FOREIGN KEY (owner_id) REFERENCES objects(id) ON DELETE CASCADE
+);
+
+CREATE TABLE IF NOT EXISTS ledger_involved_entities (
+  entry_id TEXT NOT NULL,
+  entity_id TEXT NOT NULL,
+  PRIMARY KEY (entry_id, entity_id),
+  FOREIGN KEY (entry_id) REFERENCES ledger_entries(id) ON DELETE CASCADE
+);
+
+CREATE INDEX IF NOT EXISTS idx_ledger_owner ON ledger_entries(owner_id);
+CREATE INDEX IF NOT EXISTS idx_ledger_location ON ledger_entries(location_id);
+CREATE INDEX IF NOT EXISTS idx_ledger_importance ON ledger_entries(importance);
+CREATE INDEX IF NOT EXISTS idx_ledger_involved_entity ON ledger_involved_entities(entity_id);
+```
+
+### Handoff (Deferred)
+
+The process of moving memories from the Tier 1 working buffer into Tier 2 is called **Handoff**. 
+During handoff, an LLM chunk-summarizes raw buffer events, extracts salient quotes, and assigns an `importance` score (1-10). Routine actions score low, while life-altering events score high.
+
+Because this summarization requires an LLM call, it utilizes the standard `LLMProviderInstance` inference provider routing architecture just like all other callers in the system. This allows the simulation to route handoff processing to a specific model.
+
+*Note: The automated handoff pipeline is currently deferred for future implementation.*
+
+### Retrieval Architecture
+
+Retrieval happens in phases to manage context window limits without running expensive vector searches across an entity's entire lifetime of memories.
+
+#### Phase 1: Deterministic Heuristic Filtering
+
+This is the primary database-level retrieval mechanism. We use fast SQL queries to filter down to a relevant candidate pool based on immediate context:
+
+1. **Spatial Cues**: Fetch recent memories where `location_id` equals the entity's current location.
+2. **Social Cues**: Fetch recent memories involving the `involvedEntityIds` currently in the entity's perception radius.
+3. **High Salience**: Always fetch memories with `importance >= 8` regardless of spatial or social context.
+
+#### Phase 2: Semantic & Episodic Ranking
+
+This phase runs in application memory using the candidates returned from Phase 1:
+
+1. **Semantic Match**: Compute cosine similarity dynamically in JS/TS memory over the candidate pool (limit 100). Since Phase 1 narrows the pool down significantly, vector comparisons are highly performant in JS, eliminating the need for native vector database extensions.
+2. **Scoring Combination**: Combine recency, importance, and semantic match:
+   $$\text{Score} = (\text{recencyWeight} \times \text{recency}) + (\text{importanceWeight} \times \text{importanceNorm}) + (\text{relevanceWeight} \times \text{relevance})$$
+   Where `recency` uses an exponential decay based on elapsed hours ($\text{decayRate}^{\text{hoursElapsed}}$).
+3. **Associative Chain**: When a memory is selected, automatically pull in its immediate chronological neighbors (preceding and succeeding ledger entries) to preserve episodic continuity (mirroring how remembering one event triggers the memory of what happened right after).
+
+### Retrieval Triggers & Active Focus
+
+In crowded locations (e.g. a tavern with 15 other characters), retrieving memories for all co-located entities simultaneously would cause **context explosion**. To prevent this, Omnia utilizes an **Active Focus** trigger strategy:
+
+- **Active Focus Scanning**: The prompt builder scans the last 10 entries of the entity's recent working memory (Tier 1 Buffer). Any character that the actor has recently spoken to, thought about, or was targeted by is placed in the "Active Focus" set.
+- **Dynamic Thresholding**: 
+  - If the number of co-located entities is small ($\le 3$), long-term memory is retrieved for all of them.
+  - If the location is crowded ($> 3$ entities), the system **strictly** limits long-term retrieval to the top 3 characters in "Active Focus".
+- This creates a natural attention loop. When a new character interacts with the actor, they immediately enter "Active Focus" in the buffer, triggering the retrieval of their long-term history on the subsequent turn.
+
+### Integration into Prompts
+
+Recalled entries are formatted into the prompt using chronological relative time grouping. System-level metrics like salience/importance scores are omitted to preserve immersion, and system UUIDs are mapped to subjective aliases.
+
+To frame the prompt naturally:
+1. Tier 1 working buffer entries are presented under the header `=== RECENT EVENTS ===`, referring strictly to events happening in the present narrative context.
+2. Tier 2 recalled entries are presented under the header `=== YOUR MEMORIES ===`, framing them simply as the entity's memories.
+
+```text
+=== RECENT EVENTS ===
+Moments ago
+  - you spoke to Strider: "Hello there"
+
+=== YOUR MEMORIES ===
+A couple days ago
+  - You met a hooded figure named Strider at The Prancing Pony.
+    Quote: "I can avoid being seen, if I wish, but to disappear entirely, that is a rare gift."
+```

web/docs/wrangler.jsonc

@@ -0,0 +1,14 @@
+{
+  "$schema": "node_modules/wrangler/config-schema.json",
+  "name": "omnia-docs",
+  "compatibility_date": "2026-07-09",
+  "assets": {
+    "directory": "./dist"
+  },
+  "routes": [
+    {
+      "pattern": "omnia.adityagupta.dev/docs*",
+      "zone_name": "adityagupta.dev"
+    }
+  ]
+}