# repo-memory

> Use this tool when you need to persist and share knowledge across AI agent sessions or teammates, solving problems of data loss and inconsistency. The repo-memory tool stores knowledge as plain files in a repository directory, using Git as a sync layer to automatically pick up learned information. It takes in repository data and outputs a shared knowledge base, ideal for use cases where continuity and collaboration are crucial.

Canonical page: https://skillsregistry.net/skills/yubinkim444-repo-memory  
JSON: https://api.skillsregistry.net/v1/skills/yubinkim444-repo-memory

## Description

A different approach from typical persistent-memory MCPs. Instead of a local
SQLite + embeddings store, the memory lives as plain files in a .ai-memory/
directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md).
Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the
next session (or a teammate's agent) picks up automatically.

5 MCP tools: get_rep

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/u8op6m68ox)
- **Repository:** <https://github.com/yubinkim444/repo-memory>

## 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": "yubinkim444-repo-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yubinkim444-repo-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yubinkim444-repo-memory/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