iikarus/Dragon-Brain
47 stars · Last commit 2026-05-28
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.
README preview
# 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) **Memory infrastructure for AI agents — that fails loud, by design.** [](benchmarks/longmemeval/RESULTS.md) [](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) > **100% LongMemEval R@5** · **34 MCP tools** · **sub-200ms hybrid search** · **CI-gated fail-loud contracts** · **No LLM required**