# Cognee Documentation

> Cognee turns documents, code, and application data into persistent AI memory that agents and applications can store, query, and improve over time.

## Recommended Entry Points

- [Getting Started](https://docs.cognee.ai/getting-started/introduction.md): Start here for installation, quickstart, and the core memory model.
- [Cognee MCP Overview](https://docs.cognee.ai/cognee-mcp/mcp-overview.md): Best entry point for using Cognee from Cursor, Claude Code, and other MCP clients.
- [Cognee Cloud Overview](https://docs.cognee.ai/cognee-cloud/overview.md): Managed product docs for Cloud features, connections, UI, and team workflows.
- [REST API Reference](https://docs.cognee.ai/api-reference/introduction.md): HTTP API docs for building against Cognee services.
- [Python API Reference](https://docs.cognee.ai/python-api.md): Python API docs for using Cognee directly in code.

## Documentation Shards

- [Cognee Core Documentation](https://docs.cognee.ai/llms-core.md): Getting started, concepts, setup, guides, examples, and contributor docs.
- [Cognee Cloud Documentation](https://docs.cognee.ai/llms-cognee-cloud.md): Cognee Cloud onboarding, connections, functionality, and UI documentation.
- [Cognee MCP Documentation](https://docs.cognee.ai/llms-mcp.md): Cognee MCP setup, tools, transports, and AI client integrations.
- [Cognee Integrations](https://docs.cognee.ai/llms-integrations.md): Third-party integrations across observability, frameworks, and tooling.
- [Cognee API Documentation](https://docs.cognee.ai/llms-api.md): REST and Python API references for programmatic use.

## Notes

- `llms.txt` is the curated overview for agents and LLM tools.
- The shard pages contain the full markdown page lists for each major documentation surface.
- `llms-full.txt` remains available separately as the full-site export.