MCP server for persistent, semantic memory across AI sessions
Collective-memory is an MCP integration. MCP server for persistent, semantic memory across AI sessions.
The published npm package is collective-memory, version 0.1.2. Its declared MCP transport is stdio.
The package declares OPENAI_API_KEY (required): OpenAI API key for generating embeddings.
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. This profile uses version 0.1.2 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 developer tools MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| OPENAI_API_KEY | OpenAI API key for generating embeddings | Yes |
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.
Graph-based memory system for LLMs with knowledge graphs and semantic search.
Persistent memory shared across Claude, ChatGPT, Grok and other MCP clients.
All endpoints are available by default at `http://localhost:8000` (or your configured host/port).
97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.