garnet-mcp runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 10 Aug 2026.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Nothing serious here today
Today is the operative word: we check garnet-mcp every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Alternatives to garnet-mcp
same job, measured the same wayAssociative key-graph memory for LLM agents — recall by association, not vector similarity.
Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.
garnet-mcp — questions
Answers built from our own checks of this server.