Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation
Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation
neuromcp is the first Sovereign Memory layer for AI: an open-source MCP server that gives Claude, GPT, Gemini, and Ollama persistent, searchable memory — stored entirely on your machine. No API keys. No cloud sync. No subscription required to remember who you are.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| v0.27 | security release: CWE-22 path-traversal fix in wiki_ingest, |
| v0.26 | recall_answer (deterministic extractive answers with |
| v0.20 | 0.25** — shared HTTP daemon, session isolation, critic hook, |
claude mcp add neuromcp --env NEUROMCP_DB_PATH=your-value --env NEUROMCP_NAMESPACE=your-value -- npx -y neuromcp-init| Variable | Description | Required |
|---|---|---|
| NEUROMCP_DB_PATH | Filesystem location the server is allowed to use. | Optional |
| NEUROMCP_NAMESPACE | Configuration value read at startup. | 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.
AI coding tools are powerful, but they have blind spots when it comes to your local files:
A shared knowledge base for AI agents. Store what you discover. Search what others have learned.
arXiv URI id shape, value discarded
A Model Context Protocol (MCP) server that provides access to your Monzo banking data through a Claude tool.