Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cursor, Windsurf, VS Code Copilot. 30 tools, 1121 tests.
# Dragon Brain
[English](README.md) | [中文](README.zh-CN.md) | [日本語](README.ja.md) | [Español](README.es.md) | [Русский](README.ru.md) | [한국어](README.ko.md) | [Português](README.pt-BR.md) | [Deutsch](README.de.md) | [Français](README.fr.md)
**Persistent memory infrastructure for AI agents.**
[](LICENSE)
[](https://github.com/iikarus/Dragon-Brain/actions/workflows/ci.yml)
[](https://www.python.org/downloads/)
[](docker-compose.yml)
[]()
[]()
[-blue)]()
[]()
[](https://github.com/iikarus/Dragon-Brain/stargazers)
> **1,599 memories** · **34 MCP tools** · **Graph + Vector hybrid retrieval** · **sub-200ms search** · **1,166 tests**
An open-source MCP server that gives any LLM long-term memory using a knowledge graph + vector search hybrid. Store entities, observations, and relationships — then recall them semantically across sessions. Works with any MCP client: Claude Code, Claude Desktop, Cursor, Windsurf, Cline, Cursor CLI, VS Code Cursor, or any LLM that speaks [Model Context Protocol](https://modelcontextprotocol.io/).
Unlike flat chat history or simple RAG, Dragon Brain understands *relationships* between memories — not just similarity. An autonomous agent ("The Librarian") periodically clusters and synthesizes memories into higher-order concepts.
![Dragon Brain Dashboard — 1,599 nodes, 3,120 relationships, graph visualization and health mAgent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.