Memory LibSQL
A Go implementation of the MCP Memory Server using libSQL for persistent storage with vector search capabilities, providing a high-performance alternative to the TypeScript version with 2x performance improvement and 40% less memory footprint. The server manages knowledge graphs by storing entities, observations, and relations in libSQL databases, supporting both text-based and vector similarity search through libSQL's built-in vector capabilities. Features include multi-project support for managing separate databases per project, compatibility with both local SQLite files and remote libSQL servers like Turso, and a complete set of tools for creating entities, searching nodes, managing relations, and reading graph data, making it ideal for AI applications requiring persistent memory with fast retrieval and semantic search capabilities.
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 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · 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/zanzythebar/mcp-memory-libsql-go
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Memory LibSQL 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.