# Loopism

- **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:** [Umar Ghani](https://cerebralvalley.ai/u/UmarGhani), [Aidan Chen](https://cerebralvalley.ai/u/aidanchen00)
- **GitHub:** https://github.com/aidanchen00/loopism
- **Demo video:** https://www.loom.com/share/53ceb35aa8a04768aca64bff1a4362ae
- **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/16

Most AI music tools are static—they ship a model and that's it. The prompt you write is the prompt you get. Loopism takes a different approach: agents that critique their own outputs, refine the prompt, and try again. Each generation learns from the last. Over time, the system builds a memory of what works and applies it automatically. It's not just generating music, it's learning how to generate better music.

## More from WeaveHacks 3: Self-Improving Agents Hackathon with Weights & Biases

- [Raphael](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/13)
- [SexySecurity](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/14)
- [Hypernym](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/15)
- [Stake Chess: LLM-Guided RL Training for Human Tendency Exploitation](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/17)
- [Benchmark: Moltbook self improving agents](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/18)
- [SmartChat](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/19)

---

Markdown version of https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/16. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt