Command Palette

Search for a command to run...

UnylyUnyly
Browse all

Threadwork

FreeNot checked

A multi-agent collaboration tool for Claude Code that supports hot-swappable role YAML, persistent memory with SQLite and FTS5, and step-level replay in a singl

GitHubEmbed

About

A multi-agent collaboration tool for Claude Code that supports hot-swappable role YAML, persistent memory with SQLite and FTS5, and step-level replay in a single-file HTML viewer.

README

threadwork

Threadwork

English | 简体中文

给 Claude Code 的多 Agent 协作工具:角色 yaml 热插拔 + 持久记忆 + step-level replay。 CLI-native multi-agent collaboration for Claude Code.

CI License: MIT npm version Node

快速上手

npm install -g threadwork-cli
threadwork init                # 自动注册 MCP 到 ~/.claude.json(带备份 + 原子重命名)
threadwork roles list          # 看一眼默认的四个角色

然后在 Claude Code 里直接调用 threadwork 技能;任务跑完后用 threadwork replay <task_id> 看 step-level 时间线(--serve 直接打开浏览器)。

Demo

asciinema 脚本在 bench/demo.cast。本地用 node bench/build-gif.mjs 渲染成 GIF(需要 PATH 上有 agg),渲染产物 bench/demo.gif 已 commit,CI 卡死 ≤2 MB。

为什么不用 X

需求 ruflo deer-flow Threadwork
不 fork 就能自定义角色 否 — 16 个角色硬编码 部分 — 改代码 是 — 一个 yaml 一个角色
不重启就能改角色 是 — chokidar 监听,<500 ms
原生跑在 Claude Code 里 否 — 独立 Python server 否 — 独立 Python server 是 — npm + MCP,无独立守护
任务级 replay 是 — 单文件静态 HTML viewer
跨 session 持久记忆 部分 — 向量库 是 — SQLite + FTS5,内容哈希去重
没有 vendor 锁

定位:ruflo 但角色不硬编码;deer-flow 但带个 debugger。

三块东西

可独立使用,也可组合:

  1. 可热插拔的角色 yaml。 把 yaml 丢进 ~/.threadwork/roles/./.threadwork/roles/(项目级覆盖全局),loader 实时拾取, 不用重启 Claude Code。
  2. 持久记忆 MCP server。 SQLite + FTS5 覆盖 episodes / facts / working context;recall 用 bm25 排序。无 embedding,无 consolidation; v0.1 故意保持小。
  3. Step-level trace replay。 每个 memory 调用都自动记 trace。 threadwork replay <task_id> 渲染单文件 HTML,分角色 swim-lane + 点击查看详情面板。无前端框架,无服务端。

状态

预发布,闭源 alpha 阶段。详见 docs/internal/alpha-beta.md(闭源 beta 计划与反馈渠道)。MIT 许可证。

文档

License

MIT — 见 LICENSE

from github.com/Tianqi-Bu/threadwork

Installing Threadwork

This server has no published package — it is built from source. Open the repository and follow its README.

▸ github.com/Tianqi-Bu/threadwork

FAQ

Is Threadwork MCP free?

Yes, Threadwork MCP is free — one-click install via Unyly at no cost.

Does Threadwork need an API key?

No, Threadwork runs without API keys or environment variables.

Is Threadwork hosted or self-hosted?

Self-hosted: the server runs locally on your machine via the install command above.

How do I install Threadwork in Claude Desktop, Claude Code or Cursor?

Open Threadwork on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.

Related MCPs

Compare Threadwork with

Not sure what to pick?

Find your stack in 60 seconds

Author?

Embed badge for your README

Browse similar

All data MCPs