Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.
Graph-Mem is an MCP integration. Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.
The published pypi package is graphmem-mcp, version 1.0.0. Its declared MCP transport is stdio.
The package declares GRAPHMEM_DB_PATH: Path to the SQLite database file. Defaults to .graphmem/graph.db relative to the working directory.; GRAPHMEM_EMBEDDING_MODEL: sentence-transformers model ID used for semantic search. Defaults to all-MiniLM-L6-v2, downloaded on first use.; GRAPHMEM_TRAVERSAL_NODE_BUDGET: Maximum entities visited by a single graph traversal. Defaults to 5000.; GRAPHMEM_LOG_LEVEL: Logging verbosity: DEBUG, INFO, WARNING, ERROR, or CRITICAL. Defaults to WARNING..
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository · Project website. This profile uses version 1.0.0 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related other integrations MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| GRAPHMEM_DB_PATH | Path to the SQLite database file. Defaults to .graphmem/graph.db relative to the working directory. | Optional |
| GRAPHMEM_EMBEDDING_MODEL | sentence-transformers model ID used for semantic search. Defaults to all-MiniLM-L6-v2, downloaded on first use. | Optional |
| GRAPHMEM_TRAVERSAL_NODE_BUDGET | Maximum entities visited by a single graph traversal. Defaults to 5000. | Optional |
| GRAPHMEM_LOG_LEVEL | Logging verbosity: DEBUG, INFO, WARNING, ERROR, or CRITICAL. Defaults to WARNING. | Optional |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Turn your Pieces Long-Term Memory into an AGENTS.md your coding agents can read.
An MCP (Model Context Protocol) server for image conversion using ImageMagick and darktable.
zk-mcp is an MCP (Model Context Protocol) server for integrating notes managed by zk with LLMs. It enables LLMs to efficiently access and interact with knowledge bases managed under zk.
Vehicle specs, federal recalls, and OBD-II DTC reference for AI agents via MCP.