# Mengram Docs

## Docs

- [Agent Memory](https://docs.mengram.io/agent-memory.md): Give your AI agents persistent memory with agent_id scoping, run tracking, and procedural learning.
- [API Reference](https://docs.mengram.io/api-reference.md): Complete REST API documentation for Mengram with all endpoints, parameters, and response formats.
- [Async Client](https://docs.mengram.io/async-client.md): Non-blocking Python client built on httpx for async/await workflows.
- [Claude Code Integration](https://docs.mengram.io/claude-code.md): Full memory loop for Claude Code — auto-save conversations, auto-recall context on every prompt, and load your profile on session start.
- [CLI Reference](https://docs.mengram.io/cli.md): Command-line interface for Mengram — setup, MCP server, data import, hooks, and rules generation.
- [Cognitive Profile](https://docs.mengram.io/cognitive-profile.md): Generate a ready-to-use system prompt from memory that captures who a user is, their preferences, and current focus.
- [CrewAI](https://docs.mengram.io/crewai.md): Give your CrewAI agents persistent memory with procedural learning.
- [Mengram Documentation](https://docs.mengram.io/index.md): The memory layer for AI apps. Persistent memory — semantic, episodic, procedural — with native quality across 23 languages.
- [JavaScript SDK](https://docs.mengram.io/javascript-sdk.md): Node.js and browser SDK for Mengram with full TypeScript support.
- [LangChain](https://docs.mengram.io/langchain.md): Use MengramRetriever in LangChain RAG pipelines and chains for persistent memory.
- [Claude Managed Agents](https://docs.mengram.io/managed-agents.md): Give Claude Managed Agents persistent memory with Mengram's MCP server — 29 tools for semantic, episodic, and procedural memory.
- [MCP Server](https://docs.mengram.io/mcp-server.md): Use Mengram as a Model Context Protocol server with Claude Desktop, Cursor, Windsurf, and other MCP clients.
- [Memory Types](https://docs.mengram.io/memory-types.md): Understand semantic, episodic, and procedural memory — the three pillars of human-like AI memory.
- [n8n Integration](https://docs.mengram.io/n8n.md): Add persistent memory to any n8n AI agent workflow with a ready-to-import template.
- [OpenClaw Plugin](https://docs.mengram.io/openclaw.md): Give your OpenClaw agent persistent memory with auto-recall, auto-capture, and 12 memory tools.
- [Python SDK](https://docs.mengram.io/python-sdk.md): Full reference for the Mengram Python client — zero external dependencies, works everywhere.
- [Quickstart](https://docs.mengram.io/quickstart.md): Get your API key and add your first memory in under 2 minutes.
- [Search & Filters](https://docs.mengram.io/search-filters.md): Semantic search, metadata filters, graph traversal depth, and unified search across all memory types.
- [Self-hosting](https://docs.mengram.io/self-hosting.md): Run Mengram on your own infrastructure with Docker Compose — PostgreSQL, Redis, and Mengram API in one command.
- [Webhooks](https://docs.mengram.io/webhooks.md): Real-time notifications when memories are created, updated, or deleted.

## OpenAPI Specs

- [openapi](https://docs.mengram.io/api-reference/openapi.json)

## Optional

- [Website](https://mengram.io)
- [GitHub](https://github.com/alibaizhanov/mengram)
- [Get API Key](https://mengram.io/#signup)