elvismdev/mem0-mcp-selfhosted
by Various
Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama while using Claude as the main LLM.
MCP
elvismdev/mem0-mcp-selfhosted
Added 1 June 2026
Overview
This tool provides a self-hosted memory server for Claude Code using the MCP protocol. It stores conversation history in Qdrant for vector embeddings and Neo4j for graph relationships, with Ollama generating local embeddings while Claude acts as the primary LLM.
Best for
Best for
Developers who want a self-hosted, privacy-controlled memory backend for Claude Code
Use cases
- Persisting conversation context across Claude Code sessions
- Building a long-term memory system for AI coding assistants
- Running a fully self-hosted memory stack for privacy-sensitive projects
Notes
This tool provides a self-hosted memory server for Claude Code using the MCP protocol. It stores conversation history in Qdrant for vector embeddings and Neo4j for graph relationships, with Ollama generating local embeddings while Claude acts as the primary LLM.
87 stars on GitHub. Last updated 2026-03-13. Licensed MIT.
Use cases
- Persisting conversation context across Claude Code sessions
- Building a long-term memory system for AI coding assistants
- Running a fully self-hosted memory stack for privacy-sensitive projects
Pros
- Full data control through self-hosting all components
- Uses well-known open-source tools like Qdrant, Neo4j, and Ollama
- Direct integration with Claude Code, a widely used coding assistant
Cons
- Requires managing multiple external services (Qdrant, Neo4j, Ollama)
- Low community adoption with only 87 GitHub stars
- Setup complexity due to manual configuration and deployment
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Full data control through self-hosting all components
- Uses well-known open-source tools like Qdrant, Neo4j, and Ollama
- Direct integration with Claude Code, a widely used coding assistant
Cons
- Requires managing multiple external services (Qdrant, Neo4j, Ollama)
- Low community adoption with only 87 GitHub stars
- Setup complexity due to manual configuration and deployment
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Qdrant
Community
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
ollama
Community
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.