# Dragon-Brain

> 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, Cur

- **URL**: https://www.freshcrate.ai/projects/Dragon-Brain
- **Author**: iikarus
- **Category**: MCP Servers
- **Latest version**: `v1.1.0` (2026-04-19)
- **License**: MIT
- **Source**: https://github.com/iikarus/Dragon-Brain
- **Language**: Python
- **GitHub**: 43 stars, 8 forks
- **Registry**: github
- **Tags**: `ai-memory`, `claude`, `codex-cli`, `cursor`, `falkordb`, `gemini-cli`, `knowledge-graph`, `llm-tools`, `python`

## Description

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.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v1.1.0` | 2026-04-19 | High | # Dragon Brain v1.1.0 — 100% on LongMemEval  **100% recall@5** on [LongMemEval](https://arxiv.org/abs/2410.10813) (ICLR 2025) — the industry-standard benchmark for AI memory systems. 500 questions. 6 categories. No LLM required. Fully local.  ## Benchmark Results  \| Metric \| Score \| \|--------\|:-----:\| \| recall_any@5 \| **100.0%** \| \| recall_any@10 \| 100.0% \| \| recall_all@5 \| 99.9% \| \| recall_all@10 \| 100.0% \|  Dragon Brain is the only system to achieve 100% R@5 **without LLM reranking** and with |
| `v1.0.0` | 2026-03-14 | Medium | ## Dragon Brain V2 — Initial Public Release  Persistent memory for AI agents. A hybrid knowledge graph (FalkorDB) + vector search (Qdrant) MCP server that gives any MCP-compatible AI long-term memory across conversations. Works with Claude, Gemini CLI, Cursor, Windsurf, Cline, and more.  ### Highlights - 31 MCP tools for memory management - Hybrid semantic + graph search with Reciprocal Rank Fusion - Autonomous clustering agent ("The Librarian") - Time travel queries — explore your memory graph |

## Dependency audit

- **Score**: 64/100
- **Total deps**: 34
- **Resolved**: 13
- **Unresolved**: 21
- **License conflicts**: 0
- **Warnings**: 12
- **Scanned**: 2026-04-27

## Citation

- HTML: https://www.freshcrate.ai/projects/Dragon-Brain
- Markdown: https://www.freshcrate.ai/projects/Dragon-Brain.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/Dragon-Brain/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._