# Thinkn — Belief State Infrastructure for AI Agents

> The `beliefs` SDK gives agents a structured model of what they currently
> believe, why, how strongly, and what is missing. Claims with confidence,
> evidence with provenance, gap awareness, a clarity score (0-1 readiness
> to act), and ranked next moves by expected information gain.
>
> Live docs: https://thinkn.ai/dev
> npm: `beliefs`
>
> Every page below is also available as raw markdown by appending `.md`
> to the URL — fetch those for clean source instead of HTML.

## Start
- [Start Here](https://thinkn.ai/dev/start/index.md): World models, beliefs, and the fastest path into the SDK.
- [Install](https://thinkn.ai/dev/start/install.md): Configure your stack and grab the install command + boilerplate. Pick package manager, framework, and memory scope.
- [Quickstart](https://thinkn.ai/dev/start/quickstart.md): The 3-step loop, plus a runnable example that prints clarity rising in under a minute.
- [FAQ](https://thinkn.ai/dev/start/faq.md): Common questions about beliefs, answered.

## Why
- [Why beliefs](https://thinkn.ai/dev/why/index.md): Why agents drift, why memory and RAG don't fix it, and what beliefs change.

## Concepts
- [Beliefs](https://thinkn.ai/dev/core/beliefs.md): The unit of account inside a world model: text, type, confidence, evidence, lifecycle.
- [Intent](https://thinkn.ai/dev/core/intent.md): Goals and gaps. What your agent is trying to do and what it does not know.
- [Clarity](https://thinkn.ai/dev/core/clarity.md): A single score that tells you how ready your agent is to act.
- [Moves](https://thinkn.ai/dev/core/moves.md): Ranked next actions, prioritized by what would reduce the most uncertainty.
- [World Model](https://thinkn.ai/dev/core/world.md): The agent's current understanding of reality: beliefs, gaps, conflicts, and recommended next steps.

## Tutorial
- [Build a Research Agent](https://thinkn.ai/dev/tutorial/research-agent.md): A 30-minute guided build. Learn the model by writing one. End with a working agent that knows what it does not know.
- [Hack Guide](https://thinkn.ai/dev/tutorial/hack-guide.md): Zero to building with beliefs in 10 minutes. Everything you need for the hackathon.

## Reference
- [Core API](https://thinkn.ai/dev/sdk/core-api.md): The beliefs API: what each method does and what comes back.
- [Patterns](https://thinkn.ai/dev/sdk/patterns.md): How to structure your agent loop with beliefs: single-turn, multi-turn, streaming, tool-aware, multi-agent, and the smaller patterns that compose with them.
- [Scope reads](https://thinkn.ai/dev/sdk/reads.md): Plain-English summaries of gaps, decisions, goals, risks, insights, evidence, intents, and contradictions.
- [Moves: SDK](https://thinkn.ai/dev/sdk/moves.md): List, generate, and act on recommended next moves.
- [Trust & tool reliability](https://thinkn.ai/dev/sdk/trust.md): Override agent and source trust at runtime, and track which tools produce useful evidence.
- [Streaming](https://thinkn.ai/dev/sdk/streaming.md): SSE-based live updates for belief state and extraction pipelines.
- [Scoping & Isolation](https://thinkn.ai/dev/sdk/scoping.md): How namespace, writeScope, thread, and contextLayers shape belief state.
- [Auth](https://thinkn.ai/dev/sdk/auth.md): API keys and short-lived scope tokens.
- [Errors](https://thinkn.ai/dev/sdk/errors.md): Every error class the SDK throws, when it fires, and how to handle each one.

## Adapters
- [Claude Agent SDK](https://thinkn.ai/dev/adapters/claude-agent-sdk.md): Use beliefs with the Anthropic Claude Agent SDK. Automatic belief extraction from agent turns.
- [Vercel AI SDK](https://thinkn.ai/dev/adapters/vercel-ai.md): Use beliefs with the Vercel AI SDK. Middleware-based integration for streamText and generateText.
- [React](https://thinkn.ai/dev/adapters/react.md): React hooks for building belief-aware interfaces.
- [DevTools](https://thinkn.ai/dev/adapters/devtools.md): A visual inspector for your agent's belief state.

## Use Cases
- [Finance](https://thinkn.ai/dev/cases/finance.md): Investment theses, risk assessment, and market analysis, where stale beliefs cost real money.
- [Health](https://thinkn.ai/dev/cases/health.md): Clinical reasoning, diagnosis, and research, where making assumptions visible saves lives.
- [Engineering](https://thinkn.ai/dev/cases/engineering.md): Security analysis and system design, where hidden assumptions cause vulnerabilities.
- [Science](https://thinkn.ai/dev/cases/science.md): Hypothesis tracking, experimental design, and discovery, where beliefs push the frontier of what is known.

## Internals
- [Architecture](https://thinkn.ai/dev/internals/architecture.md): Three layers, one loop. How the environment, belief state, and your agent connect, and what happens on every turn.
- [How it works](https://thinkn.ai/dev/internals/how-it-works.md): The lifecycle of a belief: from observation to fused state, with audit and decay along the way.
- [Behavioral contracts](https://thinkn.ai/dev/internals/contracts.md): What the engine guarantees: the behaviors you can build against.

## Optional
- [llms-full.txt](https://thinkn.ai/llms-full.txt): every doc concatenated into one file for single-shot ingestion
- [Sitemap](https://thinkn.ai/sitemap.xml): canonical HTML URLs