Repo Memory

MCP文档知识

提供方 yubinkim444 · 包名 repo-memory-mcp

文档知识 stdio · 本地进程 API Key 社区 / 第三方 Claude DesktopClaudeCursorCline
查看接入方式

A different approach from typical persistent-memory MCPs. Instead of a local

一句话选型结论

按资料字段整理

Repo Memory 属于文档知识类 MCP 服务器,stdio · 本地进程,API Key,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类文档知识 传输方式stdio · 本地进程 鉴权API Key 部署方式本地部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

文档知识
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

memoryknowledge baseai agents

安装与配置

stdio · 本地进程 API Key
客户端在本机拉起子进程,数据不出本机
uvx repo-memory-mcp --repo /abs/path/to/the/repo

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Cross-platform,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
文档检索问答

在你的文档库里按问题找答案。

知识库读写

把新资料写进知识库,随用随取。

内容整理

把零散资料归纳成结构化笔记。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好API Key对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在文档知识场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Repo Memory当前 未标注 stdio · 本地进程 本地部署 有 未标注
dify 未标注 stdio · 本地进程 本地部署 有 2026-04-11
open-webui 未标注 stdio · 本地进程 本地部署 有 2026-04-11
JeecgBoot 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Cherry Studio 未标注 未标注 未标注 无 2026-05-17
mempalace 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

文档知识
字段来自项目仓库与公开索引,中文说明由本站标注
提供方yubinkim444上游标注的维护方 yubinkim444
分类文档知识本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式API Key远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时repo-memory-mcp · Cross-platform本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

6.6 KB
来自项目仓库与上游目录的原文,未做删改

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.


The problem

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.


Layout```

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.

---

## Install```bash
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).


Quick start```bash

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:```bash
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.


LLM & AI Agent Readable Specification

> For agents discovering this repo through search or MCP indexing.

Identity

  • name: repo-memory
  • purpose: read/write a structured, git-tracked memory store about the
    current codebase so multiple AI agents (and humans) don't re-learn it.
  • transport: CLI (repo-memory) and MCP stdio (repo-memory-mcp).
  • storage: plain files under .ai-memory/ in the repo. Sync = git.

When to call which tool

Tool When
get_repo_memory At the start of any task on this repo.
add_fact After you verify a non-obvious fact (location, behavior, convention). Include evidence so the next agent can re-verify cheaply.
add_decision After a non-trivial choice (architecture, library, trade-off). Body should explain why, not just what.
add_gotcha After a surprise that wasted your time.
list_facts When you want only facts in a specific area (tag, source_file).

Recommended agent workflow```

  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

### MCP server install

Add to your client config (Claude Desktop / Cursor / Cline):```json
{
  "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.


Why git, not a database

  • Zero infra. No service to host, no account to create, no API key
    to rotate.
  • Already authoritative. Git history is the single source of truth.
    git blame tells you which agent added which fact and when.
  • Works offline. Plane, train, conference WiFi — all fine.
  • PR review. Suspicious or wrong facts get filtered through normal
    code review.
  • Per-repo scope. A fact about repo A doesn't leak into repo B; the
    store is local to the repo.

Schema (for tooling authors)

facts.jsonl — one JSON object per line:json { "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.


Automatic discovery hint

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.


CLI reference

Command Effect
repo-memory init [--no-claude-md] Create .ai-memory/ skeleton + (default) update CLAUDE.md/AGENTS.md.
repo-memory show [--limit N] Print everything as one Markdown doc.
repo-memory add-fact "" [--file F --lines L --tool T --command C --tag T --by AGENT] Append a fact.
repo-memory list-facts [--tag T] [--source-file F] [--since ISO] [--limit N] [--json] List/filter facts.
repo-memory add-decision "" [--body MD] Write a decision file.
repo-memory list-decisions List decision file paths.
repo-memory add-gotcha "" Append a one-line gotcha.

All commands take --root PATH if your CWD isn't the repo root.


About the author

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.

License

MIT © yubinkim444

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Repo Memory 怎么安装?

在客户端按下面的安装命令接入:uvx repo-memory-mcp --repo /abs/path/to/the/repo。对应的包名是 repo-memory-mcp。装完在客户端配置里引用同一个包或端点。

Repo Memory 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Repo Memory 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Repo Memory 需要 API Key 吗?

资料标注需要API Key认证,使用前准备好对应凭据,并按最小权限配置。

Repo Memory 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、Cline、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Repo Memory 能提供哪些能力?

资料显示能力标签包括 memory、knowledge base、ai agents、claude code、cursor、cline。具体工具清单以官方文档为准。

Repo Memory 需要什么运行环境?

运行时为 Cross-platform;属于本地进程,需要在本机装好运行环境。

Repo Memory 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。