# gitmem

> gitmem — gitmem-dev-gitmem. Use this tool when you need to retain institutional memory for AI coding agents, storing scars, wins, and patterns that persist across sessions. It solves the problem of knowledge loss between sessions, providing a persistent memory for AI agents like Claude Code, Cursor, and OpenClaw. With git capabilities, it accepts code and pattern inputs, outputting a persistent knowledge base that informs future coding decisions.

Canonical page: https://skillsregistry.net/skills/gitmem-dev-gitmem  
JSON: https://api.skillsregistry.net/v1/skills/gitmem-dev-gitmem

## Description

Institutional memory for AI coding agents. Scars, wins, and patterns that persist across sessions. MCP server for Claude Code, Cursor, OpenClaw...

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-06-18

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-23

## Source

- **Source listing:** [GitHub](https://github.com/gitmem-dev/gitmem)

## 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": "gitmem-dev-gitmem"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gitmem-dev-gitmem` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gitmem-dev-gitmem/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