> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cruq.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> CruqAI is a platform for building, running, and observing AI agents you own.

## What is CruqAI

CruqAI lets you build LangGraph agents on your own model provider connections,
give them tools, ground them in your own knowledge, and run them with full
observability. Everything is tenant-scoped and isolated at the database level.

<CardGroup cols={2}>
  <Card title="Agents" icon="robot" href="/docs/concepts/agents">
    Visual, data-driven LangGraph agents with a ReAct tool loop.
  </Card>

  <Card title="Knowledge (RAG)" icon="book" href="/docs/concepts/knowledge">
    Knowledge bases with self-hosted embeddings and pgvector retrieval.
  </Card>

  <Card title="Memory" icon="brain" href="/docs/concepts/memory">
    Long-term facts recalled semantically across threads.
  </Card>

  <Card title="Guardrails & Prompts" icon="shield" href="/docs/concepts/guardrails-prompts">
    Input/output safety policies and a versioned prompt registry.
  </Card>
</CardGroup>

## Surfaces

* **Web app** ([app.cruq.ai](https://app.cruq.ai)) - build agents, connect
  providers, manage knowledge/memory/guardrails/prompts, and watch runs.
* **`/v1` REST API** - programmatic access, authenticated with an API key.
* **`cruqai` CLI** - run agents, stream traces, and manage resources from your
  terminal.

## How it fits together

An agent references **tools** and a **model** (via a provider connection). At run
time the runtime streams a tool-call trace you can observe live or replay later.
Agents can retrieve from **knowledge bases** and read/write **memory** through
built-in tools, all embedded by a self-hosted embedder so no external embeddings
key is required.