Graph-Mem
Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.
Open the source (opens github.com) https://github.com/sathvik-1007/graphmem-mcp
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.Sathvik-1007.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
graphmem-mcp@1.0.0
From the server's entry in the official MCP Registry
Settings it asks for
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.
Related
-
sqlite-graph-memory
MCP serversRecall over your markdown notes: vector search plus your [[wikilinks]] as a graph, in SQLite.
sqlite-graph-memory@0.3.9 -
Reverie
MCP serversGraph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
@knowall-ai/reverie@0.5.4 -
Reverie
MCP serversGraph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
@knowall-ai/reverie@0.5.1 -
mcp-neo4j-memory
MCP serversMCP Neo4j Knowledge Graph Memory Server
mcp-neo4j-memory@0.4.2 -
kg
MCP serversLocal knowledge graph memory MCP server for AI assistants.
-
shelbymcp
MCP serversKnowledge-graph memory server for AI tools via MCP
shelbymcp@0.2.4