agentleFS
sdh0219sdh0219/team-memory/AGENTS.md

team-memory

AGENTS.md2 starsChanged 22 days agoMITView on GitHub

这是 team-memory 的源码仓库,同时是 team-memory 协议的*活样例*:本仓库用自己的协议管理自己 (见 .memory/)。 1. 协议六处同步:改协议文字必须同步 skills/team-memory/SKILL.md、docs/protocol.md、 docs/protocol_EN.md、README.md、README_EN.md、examples/AGENTS.md,缺一即回工。 2. CI 会跑 scripts/validate_memory.py 校验 .memory/ 与 examples/memory/,红线:STATE ≤50 行、 LOG 单条 ≤10 行、日期新在上、不写密钥。 3. 仓库维护者本机 git 推 GitHub 需走本地代理(127.0.0.1:7897)。 开工前: 1. 读 .memory/STATE.md(必读,很短) 2. 仅当任务需要历史细节时,再查 .memory/LOG.md 和 git log --oneline -15 收工前(阶段性工作结束): 1. 更新 .memory/STATE.md:完成项移出"正在做",更新"下一步" 2. 在 .memory/LOG.md 顶部追加一条记录(日期/agent 名/结论/改动文件/遗留),≤ 10 行 纪律:STATE.md 直接改写不追加;LOG.md 只追加;细节写进 commit message; 「正在做」两周没动就更新或回退;不把密钥、token 等敏感信息写入记忆文件。

The file

Files
AGENTS.md

AGENTS.md — team-memory 仓库规则

这是 team-memory 的源码仓库,同时是 team-memory 协议的活样例:本仓库用自己的协议管理自己 (见 .memory/)。

项目结构

  • skills/team-memory/ — 记忆层技能本体;skills/team-digest/ — 周报蒸馏技能
  • docs/ — 协议规范与 FAQ(中英双语);examples/ — 示例项目记忆文件
  • scripts/ — 安装脚本(install.sh / install.ps1)与记忆校验/归档工具(validate_memory.py / archive_log.py)
  • hooks/ — Stop 钩子模板(第三道保险);.github/workflows/ — CI 校验记忆文件

硬规矩

  1. 协议六处同步:改协议文字必须同步 skills/team-memory/SKILL.md、docs/protocol.md、 docs/protocol_EN.md、README.md、README_EN.md、examples/AGENTS.md,缺一即回工。
  2. CI 会跑 scripts/validate_memory.py 校验 .memory/ 与 examples/memory/,红线:STATE ≤50 行、 LOG 单条 ≤10 行、日期新在上、不写密钥。
  3. 仓库维护者本机 git 推 GitHub 需走本地代理(127.0.0.1:7897)。

Agent 记忆协议(每个会话必做)

开工前:

  1. 读 .memory/STATE.md(必读,很短)
  2. 仅当任务需要历史细节时,再查 .memory/LOG.md 和 git log --oneline -15

收工前(阶段性工作结束):

  1. 更新 .memory/STATE.md:完成项移出"正在做",更新"下一步"
  2. 在 .memory/LOG.md 顶部追加一条记录(日期/agent 名/结论/改动文件/遗留),≤ 10 行

纪律:STATE.md 直接改写不追加;LOG.md 只追加;细节写进 commit message; 「正在做」两周没动就更新或回退;不把密钥、token 等敏感信息写入记忆文件。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.