# Silk Lab

- **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:** [Fanchao Yu](https://cerebralvalley.ai/u/evelynyu), [yan ziyuan](https://cerebralvalley.ai/u/Ryan-Yan), [xi zhao](https://cerebralvalley.ai/u/Xi06)
- **GitHub:** https://github.com/yanzai-4/silk-lab
- **Demo video:** https://youtu.be/VEzN80-P2Lw
- **Gallery:** https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/46

Silk Lab is a self-evolving research lab: a platform where a team of AI agents builds, measures and improves itself on a real research goal. You give it one goal (our applied case is Kwon Lab at Northeastern: moving gaze-contingent training for central vision loss from lab eye trackers to VR headsets and tablets). Hold-to-deploy, and a master agent hires sub-agents, organizes them into labs, and plugs in instruments with your consent. Each agent is a genome, a graph of model, tool and code nodes, and an evolution engine mutates it. A referee locks the success criteria and a held-out set before any change, so every new version must beat its parent on data it never saw, with lineage, an evidence chain and rollback. Teams evolve too: parallel structures compete and the winning one stays. A council inside the master (planner, coordinator, standards committee) votes on big decisions and steers the master's own evolution. A safety officer (hard-coded rules + Jev pre-screen + LLM review) warns on small issues and halts the whole project on critical ones until a human decides. Agents can propose new analysis panels and themes for the UI, through a validated extension API. Every researcher, on every machine, talks to the same lab through a chat module that never interrupts running work. Problem solved: research automation today means one-shot agents that never get measurably better; Silk Lab turns improvement itself into a safe, measured, held-out loop. The demo video uses mock data.

## More from The Recursive Agents Hackathon

- [BrainBob - Shared Memory](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/43)
- [manubaba](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/44)
- [Measured](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/45)
- [EvoAction](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/47)
- [Clueso](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/48)
- [Silico - comes from “in silico,” which means an experiment or simulation performed on a computer.](https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/49)

---

Markdown version of https://cerebralvalley.ai/e/crusoe-recursive-agents-hackathon/hackathon/gallery/46. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt