repo-memory
Shared, git-tracked working memory for AI agents that share a codebase. What one Claude / Cursor / Cline learns about your repo, the next one picks up automatically. No database. No SaaS. Just files in your repo.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx repo-memory-mcp==0.2.1Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
REPO_MEMORY_ROOT=<value> claude mcp add io.github.yubinkim444-repo-memory -- uvx repo-memory-mcp==0.2.1在終端機中執行。
{ "mcpServers": { "io.github.yubinkim444-repo-memory": { "command": "uvx", "args": [ "repo-memory-mcp==0.2.1" ], "env": { "REPO_MEMORY_ROOT": "<value>" } } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Shared, git-tracked working memory for AI agents that share a codebase. What one Claude / Cursor / Cline learns about your repo, the next one picks up automatically. No database. No SaaS. Just files in your repo.
Shared, git-tracked working memory for AI agents on the same codebase.
Every AI session that touches your repo starts from zero. It re-greps the same files. It re-discovers the same conventions. It re-asks the same questions you already answered three sessions ago. Multi-user / multi-tool makes it worse: your teammate's Cursor and your Claude Code learn the same codebase independently.
There is CLAUDE.md / .cursorrules for rules the human writes. But
there is nothing for facts an agent verified — "the auth middleware
lives at src/auth/middleware.py:42", "PR #387 chose httpx over requests
because of HTTP/2", "don't run migrations during peak hours".
repo-memory is that nothing. A .ai-memory/ directory you commit to
your repo. Every AI tool reads from it, writes to it. Git is the database.
your-repo/
├── .ai-memory/
│ ├── README.md # explains the convention
│ ├── facts.jsonl # append-only structured facts with evidence
│ ├── decisions/ # one markdown per non-trivial decision
│ │ └── 2026-05-19-pick-httpx.md
│ └── gotchas.md # one-line "watch out for X" notes
├── src/
└── README.md
Pure files. Sync over git. No daemon, no DB, no auth. Works offline.
pip install repo-memory-mcp
# or
uvx repo-memory-mcp --help
Python ≥3.10. Depends only on the official mcp SDK (for the MCP server).
cd your-repo
repo-memory init # creates .ai-memory/ + adds CLAUDE.md hint
repo-memory add-fact "Auth middleware lives in src/auth/middleware.py" \
--file src/auth/middleware.py --lines 42-180 --tool grep
repo-memory add-decision "Use httpx not requests" \
--body "HTTP/2 + async support; we already use anyio."
repo-memory add-gotcha "Don't run migrations during 9-11am UTC peak"
repo-memory show # render everything as Markdown
repo-memory list-facts --tag auth
Then commit .ai-memory/ like any other file:
git add .ai-memory/
git commit -m "memory: record auth middleware location + httpx decision"
git push
Anyone else (human or AI) who pulls the repo now sees those facts/decisions immediately.
For agents discovering this repo through search or MCP indexing.
repo-memoryrepo-memory) and MCP stdio (repo-memory-mcp)..ai-memory/ in the repo. Sync = git.1. agent.call("get_repo_memory") -> absorb prior context
2. ...do task, run tools, verify things...
3. agent.call("add_fact", claim, evidence) -> for each new fact
4. agent.call("add_decision", title, body) -> if a choice was made
5. session ends, human commits .ai-memory/ -> shared via git
Add to your client config (Claude Desktop / Cursor / Cline):
{
"mcpServers": {
"repo-memory": {
"command": "uvx",
"args": ["repo-memory-mcp", "--repo", "/abs/path/to/the/repo"]
}
}
}
Or set REPO_MEMORY_ROOT env var instead of --repo.
Exposes 5 tools: get_repo_memory, add_fact, list_facts,
add_decision, add_gotcha.
git blame tells you which agent added which fact and when.facts.jsonl — one JSON object per line:
{
"id": "abc123def456",
"ts": "2026-05-19T18:00:00Z",
"claim": "Auth middleware lives in src/auth/middleware.py",
"evidence": {
"file": "src/auth/middleware.py",
"lines": "42-180",
"tool": "grep",
"command": "rg 'def authenticate' src/",
"verified_at": "2026-05-19T18:00:00Z"
},
"tags": ["auth"],
"added_by": "claude-opus-4.7"
}
Append-only. Stale entries stay. Readers consult verified_at and
re-verify if they want.
repo-memory init also appends a short discoverability section to your
repo's CLAUDE.md (or AGENTS.md if you already have one) telling any
AI agent that enters the repo to check .ai-memory/ first and to record
new findings back into it. Idempotent — re-running won't duplicate.
Opt out with --no-claude-md.
The appended block is delimited by and, so you can hand-edit other parts of your
CLAUDE.md freely.
All commands take --root PATH if your CWD isn't the repo root.
Built by yubinkim444, who also makes Kay's Records — an app for iOS and Android.
If this project saved you time, giving the app a try is the nicest way to say thanks.
MIT © yubinkim444
Shared, git-tracked working memory for AI agents on the same codebase.
{ "mcpServers": { "io.github.yubinkim444-repo-memory": { "command": "uvx", "args": [ "repo-memory-mcp==0.2.1" ], "env": { "REPO_MEMORY_ROOT": "<value>" } } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
發布者列出了以下環境變數:REPO_MEMORY_ROOT。
Repo Memory 透過 stdio 在本機執行。
上次檢查時間:2026-11-10。 Shared, git-tracked working memory for AI agents on the same codebase.