agentleFS
qianzhu18qianzhu18/workisland/website/llms.txt

workisland / website

llms.txt12 starsChanged 3 months agoApache-2.0View on GitHub

WorkIsland is a free, local-first native Mac work interface for AI-native workflows. It brings local task state from coding agents such as Claude Code, Codex, and Cursor to the desktop, surfaces supported approvals or questions, and helps the user return to the originating session. In Chinese, WorkIsland is a “面向 AI 原生工作流的 Mac 桌面工作界面”. WorkIsland does not replace an agent, terminal, or IDE. It does not execute arbitrary commands, automate approvals, or upload session content, code, paths, host names, or…

  • In this repositoryOne other file it gives its agents.

The file

Files
llms.txt
# WorkIsland

> WorkIsland is a free, local-first native Mac work interface for AI-native workflows. It brings local task state from coding agents such as Claude Code, Codex, and Cursor to the desktop, surfaces supported approvals or questions, and helps the user return to the originating session. In Chinese, WorkIsland is a “面向 AI 原生工作流的 Mac 桌面工作界面”.

WorkIsland does not replace an agent, terminal, or IDE. It does not execute arbitrary commands, automate approvals, or upload session content, code, paths, host names, or user names. Email, calendar, and general-notification integrations are not shipped features.

## Product

- [Agent product brief](https://workisland.yanglaishe.cn/skill.md): Capability, requirements, limits, and a minimal start path. Approx. 220 tokens.
- [Chinese product overview](https://workisland.yanglaishe.cn/index.md): Direct definition of the AI-native Mac work interface, capability table, supported workflow, product limits, and official links.
- [English product overview](https://workisland.yanglaishe.cn/en/index.md): Direct definition of the native Mac work interface for AI-native workflows, capability table, workflow, limits, and official links.

## Guides

- [Chinese quick start](https://workisland.yanglaishe.cn/guide/index.md): Install, connect one existing agent, run a real task, and verify the return path. Approx. 360 tokens.
- [Claude Code notifications on macOS — Chinese](https://workisland.yanglaishe.cn/guides/claude-code-notifications/index.md): Fit, setup, verification, and limits for Claude Code users. Approx. 340 tokens.
- [Claude Code notifications on macOS — English](https://workisland.yanglaishe.cn/en/claude-code-notifications/index.md): Fit, setup, verification, and limits for Claude Code users. Approx. 290 tokens.

## Human-readable pages

- [Website](https://workisland.yanglaishe.cn/): Product overview and official download.
- [Product guide](https://workisland.yanglaishe.cn/guide/): Human-readable setup and privacy guide.
- [GitHub repository](https://github.com/qianzhu18/workisland): Source code, releases, and issue tracker.

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.