# Ep1cGaimer

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Vivek G](https://cerebralvalley.ai/u/vivekgn_)
- **GitHub:** https://github.com/Ep1cGaimer/cu-s1
- **Demo video:** https://youtu.be/Du9ZXTWC4Xc
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5288

cu-s1 is the fast local hand for a planning agent. Today's computer-use agents send every screenshot to a frontier model and wait for it to choose each click: slow, expensive, and a waste of the planner's attention. cu-s1 splits the job. A frontier planner (I used Muse Wonder) writes a short chain of steps; cu-s1 executes it on a Windows PC with a 2B vision model (Qwen3-VL 2B via Ollama) running locally: screenshot in, native mouse and keyboard out, each step checked on screen. If the screen doesn't match, a target can't be confirmed, focus or window geometry changes, or a step is flagged risky, it stops and hands back to the planner with a reason and a screenshot instead of guessing. It never replays an ambiguous action and never treats a pixel change as proof of success.

It ships as an MCP server (windows, look, run_steps, stop) and a local control panel that share one execution engine, with live per-step progress, a monitor view for plans arriving over MCP, cooperative stop and MCP cancellation. No accessibility APIs or app integrations: pixels only, so it works across Windows apps.

Measured (raw records in bench/runs): a live Wikipedia task 3/3 in 9.5 s; Windows Calculator 9/9 visual clicks with the answer verified on screen (16.2 s); File Explorer 3/3 (6.0 s); a request to click a non-existent button was handed back with no input sent. On matched supplied-plan holdout tasks, 3/3 at a 6.8 s median versus 25.6 s for built-in computer use; reserved holdout 8/9. These are small benchmarks, and the repo states the limits: Windows only, the 2B model is fallible, drag and multi-monitor not yet verified live.

## More from Meta Global AI Developer Hackathon

- [Disaster Management](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5285)
- [Tiku Tepi Faith](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5286)
- [qyrixx](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5287)
- [Asoro Technology](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5289)
- [CollabAI](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5290)
- [TRACEWISE](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5291)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5288. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt