[Trend Scout] iikarus/Dragon-Brain

[github-actions]

🔭 Trend Scout: iikarus/Dragon-Brain

Auto-generated by trend-scout.py — review and edit as needed.

📌 What problem it solves

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.

📅 Timeline

Field	Value
Created	2026-02-23
Last pushed	2026-06-26
Stars	50
Forks	7
Open issues	6
License	MIT
Language	Python
Topics	ai-memory, claude, codex-cli, cursor, falkordb, gemini-cli, knowledge-graph, llm-tools, mcp, memory, model-agnostic, qdrant, vector-search

✅ Strengths

• Growing community (50 ⭐)
• Well-tagged: ai-memory, claude, codex-cli, cursor, falkordb, gemini-cli
• Primary language: Python
• Actively maintained (pushed within 30 days)

⚠️ Weaknesses / Risks

• No significant risks identified from available metadata

💡 What this repo can learn

• Claude Code session patterns: this repo's Claude Code integration approach could improve claude-adapter.py's JSONL parsing — e.g., handling new session event types or extracting richer metadata from Claude Code tool-use blocks
• Hybrid FTS+semantic retrieval: combining keyword and embedding-based search could improve recall in query-session.py / briefing.py — e.g., a query for 'docker networking' would also surface entries tagged 'container' or 'network_mode' even without exact term overlap
• Graph-based knowledge linking: a relation graph over session entries could let briefing.py surface related decisions and mistakes by topic proximity — e.g., linking a mistake:auth record to pattern:jwt across separate session files without requiring identical keywords
• CLI verb patterns: a clear add/search/update/delete verb model (like memory-tool add / search / dream) could streamline the UX of query-session.py and learn.py, making them easier to invoke from hooks or scripts
• Editor integration (cursor): watch-sessions.py could be extended to detect and parse cursor session formats natively, broadening the range of AI sessions indexed into knowledge.db

README excerpt

# 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.**

[![LongMemEval](https://img.shields.io/badge/LongMemEval_R%405-100%25-gold?style=for-the-badge)](benchmarks/longmemeval/RESULTS.md)

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![CI](https://github.com/iikarus/Dragon-Brain/actions/workflows/ci.yml/badge.svg)](https://github.com/iikarus/Dragon-Brain/actions/workflows/ci.yml)
[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)
[![Docker](https://img.shields.io/badge/docker-ready-blue.svg)](docker-compose.yml)
[![MCP Tools](https://img.shields.io/badge/MCP%20tools-34-green.svg)]()
[![Tests](https://img.shields.io/badge/tests-1%2C337%20passing-brightgreen)]()
[![Contracts](https://img.shields.io/badge/contracts-CI%20gated-blue)]()
[![Gauntlet](https://img.shields.io/badge/gauntlet-A%E2%88%92%20(95%2F100)-blue)]()
[![GPU](https://img.shields.io/badge/GPU-CUDA%20supported-orange.svg)]()
[![GitHub stars](https://img.shields.io/github/stars/iikarus/Dragon-Brain)](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 req

*(truncated)*

---

Scouted on 2026-06-26 · View on GitHub

[edihasaj]

Nice work on Dragon Brain and the MCP tooling. If you are interested in a vendor-neutral memory contract to make memories portable across frameworks and vector stores, take a look at the Universal Memory Protocol project, which defines schemas, access patterns, provenance, and adapter points for exactly this use case. We have an implementation-focused repo that could be useful as a reference for building an MCP adapter or for aligning metadata and sync semantics: https://github.com/edihasaj/universal-memory-protocol