mcp-memory-service (doobidoo/mcp-memory-service) is an open-source AI project on GitHub. Repository summary: Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation. Its focus includes multi-agent orchestration, MCP and tool-calling integration, retrieval-augmented generation, workflow automation. It is suitable for extension, integration, and iterative delivery in real workflows.
License
Apache-2.0
Stars
1,893
Features
- Core capability: Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
- Supports multi-agent coordination and task decomposition
- Provides MCP or tool-calling integration
- Supports vector retrieval and retrieval-augmented reasoning
- Supports orchestrated automation flows and scheduling
- Repository: doobidoo/mcp-memory-service
Use Cases
- Used for decomposing and running complex tasks in parallel
- Connects external systems into agent workflows
- Builds enterprise knowledge Q&A and document retrieval systems
- Used for cross-system process automation and operations efficiency
- Build internal AI workflow prototypes with mcp-memory-service
- Validate mcp-memory-service in production-like engineering scenarios
FAQ
Teams should first define integration boundaries and call patterns, then map repository capabilities into concrete interfaces, parameters, and access rules. GitHub repository: https://github.com/doobidoo/mcp-memory-service. Community traction is around 1,889 stars. License: Apache-2.0.
It usually works as an execution component or capability layer, with common deployment fits such as: Used for decomposing and running complex tasks in parallel, Connects external systems into agent workflows, Builds enterprise knowledge Q&A and document retrieval systems.
