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
- fix: guard background Ollama calls against loading a second model (#111)
- [DO NOT MERGE] Test build: #107 + #108 + #115 combined for QA
- OCR is skipped silently under CPU/memory pressure, and skipped frames are never retried
- docs: recommend 16 GB RAM; 8 GB is not enough for qwen3:8b
- fix: log and retry OCR skipped under CPU/memory pressure
- Cap or document Ollama's LLAMA_ARG_CACHE_RAM so prompt cache doesn't add up to 8 GiB
- Residency / API Python stdout is block-buffered so live logs only appear on quit
- [DO NOT MERGE] Test build: #107 + #108 combined for QA
- Setup sometimes says "Python 3.11+ was not found" when it is installed (Retry finds it)
- Residency re-warms the chat model below the free-RAM floor and while another model is loaded
- Docs
- Python not yet supported