I built the assistant I clicked on as a kid. It haunts me now!
说明与用途
Paperclip 是一个本地 macOS 桌面助手,监视当前窗口,使用 Ollama 运行 Gemma 4 视觉模型,使用 Temporal 持久化状态,并且从不将截图发送到外部服务器。
问题
A user wanted a desktop assistant that could observe the screen locally, offer help, and persist across restarts without sending data externally.
结果
Paperclip provides a local, persistent, privacy‑preserving desktop assistant that observes the screen, offers context‑aware help, and survives restarts without external data leakage.
工作流
- Clone repo
- Run npm run setup to install Temporal, Ollama, and dependencies
- Configure .env and macOS permissions
- Start ghost with npm run ghost:start
- Ghost checks active window every 5 s
- When window changes, take screenshot, resize, run Gemma 4 via Ollama
- Parse JSON output {app,activity,detail,notable}
- If stuck >20 min, offer help
- Persist state in Temporal workflow
- Restart ghost via launchd if killed
证据
Paperclip runs a local vision model through Ollama, so nothing about your screen leaves your machine.
Each glance is one invoke_agent span in Sentry, with every step nested under it.
The biggest speed win came from asking for less. Instead of a paragraph, the model now returns a small JSON object: {app, activity, detail, notable}.
- 记录日期: 2026-11-02T05:43:57.339Z