# Morgadarsha

- **Event:** [The Harness Engineering & Model Wrangling Hackathon](https://cerebralvalley.ai/e/mongodb-nyc-hackathon)
- **When:** Sat, Sep 26 at 9:00 AM – 10:00 PM (EDT)
- **Where:** New York, NY
- **Placement:** Finalist
- **Team:** [Adarsha Mishra](https://cerebralvalley.ai/u/pass), [Morgan Le](https://cerebralvalley.ai/u/lhnm)
- **GitHub:** https://github.com/lhnminh/recursive-computer-use
- **Demo video:** https://youtu.be/x6hrG1wZUH4
- **Gallery:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/69

Recursive Computer Use is a local-first desktop automation harness that enables AI agents to execute tasks on your computer, verify outcomes locally, and capture privacy-filtered evidence to improve future runs. Policy changes are tightly controlled and must pass deterministic evaluations before being accepted.

It uses MongoDB as a shared memory layer across agents, allowing knowledge and experience gained from one task to be reused by others. As a result, each completed task helps accelerate future executions across all agents connected to the same memory database.

## More from The Harness Engineering & Model Wrangling Hackathon

- [Da Vinci: Recursive Improvement CAD Harness](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/11)
- [Offload](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/45)
- [AI Lobang](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/52)
- [CyclopsDiary](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/58)
- [Sightline](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/63)
- [UltraPM Console](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/93)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/69. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt