doobidoo/mcp-memory-service

Health v2 · maintenance only

Adoption not part of the score

1907 stars · 291 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A self-hosted persistent memory service for AI agents and Claude, exposing storage and semantic retrieval via REST API, MCP, OAuth, CLI, and a dashboard. It supports shared causal knowledge graphs and autonomous memory consolidation across frameworks like LangGraph, CrewAI, and AutoGen.

Use cases

• give my ai agent persistent long-term memory
• share memory between multiple ai agents in a pipeline
• add memory to claude desktop via mcp
• store and semantically search agent decisions and context
• self-host a memory backend without cloud api costs
• build a knowledge graph of agent conversations
• remember project context across chat sessions

When to choose

• you need persistent, shared memory for agent frameworks like LangGraph, CrewAI, or AutoGen
• you want a self-hosted MCP memory server with REST and OAuth support
• you need fast semantic retrieval with knowledge graph relationships and no cloud lock-in

When to avoid

• you only need simple key-value session storage without semantic search
• you prefer a fully managed cloud memory service
• your stack cannot run a Python service or SQLite-based vector store

Facets

service · maturity active

vector-database rag mcp search-engine api-framework self-hosted large-language-models databases self-hosted developer-tools python self-hosted cross-platform cli agent-memory mcp-server knowledge-graph semantic-search sqlite-vec long-term-memory multi-agent claude langgraph crewai autogen memory-consolidation ai-agents retrieval-augmented-generation docker web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="doobidoo/mcp-memory-service")