Mem0
A self-hosted memory system that provides persistent, intelligent memory capabilities through dual-server architecture combining Mem0 AI with MCP protocol integration. Built by Subhash Dasyam, it features automatic project isolation, smart text chunking for large inputs, and advanced graph intelligence through Neo4j for tracking memory relationships, decision rationale, and knowledge evolution over time. The implementation supports multiple LLM providers (Ollama, OpenAI, Anthropic) with configurable embedding models, includes token-based authentication, and offers both vector search through PostgreSQL/pgvector and graph analysis capabilities, making it ideal for developers who want context retention, preferences, and project-specific knowledge across sessions while maintaining complete data privacy through local deployment.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/subhashdasyam/mem0-server-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Mem0 from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.