# Memory LibSQL

> Use this tool when you need to manage knowledge graphs with high-performance persistent storage and vector search capabilities. It solves problems of efficient data retrieval and semantic search in AI applications, accepting inputs such as entities, observations, and relations, and outputting search results and graph data. Ideal for use cases requiring fast and scalable memory management, such as natural language processing and machine learning models.

Canonical page: https://skillsregistry.net/skills/zanzythebar-memory-libsql  
JSON: https://api.skillsregistry.net/v1/skills/zanzythebar-memory-libsql

## Description

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.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/zanzythebar-memory-libsql)
- **Repository:** <https://github.com/zanzythebar/mcp-memory-libsql-go>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "zanzythebar-memory-libsql"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zanzythebar-memory-libsql` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zanzythebar-memory-libsql/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt