Dragon Brain
未认领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.
安装
claude mcp add dragon-brain -- python -m claude_memory.server工具（10 个）
add_observation
Attach a fact or note to an existing entity
create_entity
Store a new person, project, concept, or any typed node
create_relationship
Link two entities with a typed, weighted edge
get_hologram
Get an entity with its full connected context (neighbors, observations, relationships)
get_neighbors
Explore what's directly connected to an entity
graph_health
Get stats on your memory graph — node counts, edge density, orphans
point_in_time_query
Query the graph as it existed at a specific timestamp
record_breakthrough
Mark a significant learning moment for future reference
search_memory
Semantic + graph hybrid search across all memories
semantic_radar
Discover missing relationships via vector-graph gap analysis