# Swarm

- **Event:** [The Recursive Agents Hackathon](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon)
- **When:** Sat, Oct 17 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [Marc Smeds](https://cerebralvalley.ai/u/mcsmeds)
- **GitHub:** https://github.com/TurpoFIN/swarm
- **Demo video:** https://youtu.be/fxmAXGh5VcU
- **Gallery:** https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/109

Swarm takes a big software spec, recursively splits it into a tree of small tasks and runs hundreds of real agents on them at once. Each agent sees only the context it needs: a shared-context filter decides what it keeps, drops and shares with the others, interface escrow and post-merge broadcasts keep the pieces fitting together, and failed agents retry and recover. The live app shows every agent's context window and why each choice was made. On a real run with Nemotron on Crusoe, 283 agents passed 67 of 67 tests in 29 minutes for 2.23 USD; the same model alone on the same spec passed 22 of 67.

## More from The Recursive Agents Hackathon

- [supplier-chief-of-staff](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/1)
- [icomppower.com](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/2)
- [Mato](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/3)
- [HelloTiger](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/106)
- [The A team](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/107)
- [AutoRoboHarness](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/108)

---

Markdown version of https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/109. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt