clippy-vision
https://github.com/protocorn/clippy-vision
Python
Fully local AI assistant that watches your screen to eliminate the context problem. No cloud. No data leakage.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to clippy-vision
Help out
- Issues
- Startup / residency warm-up call sends no think:false, so qwen3 generates hundreds of tokens on "ping"
- fix: skip aggressive qwen3 re-warm and send think:false on warmup
- Residency skip re-warm logs spam and sets backlog last_error to "text model unavailable"
- Residency "another model loaded" guard covers warm only — summarizer/chat can still load 8b
- Setup: bundle Python so users don't need a system Python 3.11+
- Setup: pick a small default Ollama model and download it automatically
- Unsigned builds trigger SmartScreen and OS warnings that scare off new users
- Onboarding: show a first useful answer on day one
- Linux: idle time never detected without xprintidle (fallback calls nonexistent `xdotool get_idle_time`)
- Linux AppImage: Connect apps MCP config may break after restart (points at temporary mount path)
- Docs
- Python not yet supported