# Zypharmini

- **Event:** [WeaveHacks 3: Self-Improving Agents Hackathon with Weights & Biases](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80)
- **When:** Jan 31 at 9:00 AM – Feb 1 at 5:00 PM (PST)
- **Where:** 400 California St, San Francisco, CA
- **Team:** [Yeabsira Mulugeta](https://cerebralvalley.ai/u/YAB)
- **GitHub:** https://github.com/xenn0010/zyphargatev1
- **Demo video:** https://www.loom.com/share/e640f7cfc70d490281a3b724bc298516
- **Gallery:** https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/21

Zypharmini is a World model powered agent that learns how to design chips. A working chips. it starts with generating random rtl and then use the tools from aule-technologies to verify and then correct itself till it gets it, it uses weave to trace previous runs and see if it can extract more knowledge from it

---

Markdown version of https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/21. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt