# AgentGym

- **Event:** [Gemini 3 Hackathon SF](https://cerebralvalley.ai/e/gemini-3-hack-sf)
- **When:** Sat, Dec 6 at 9:00 AM – 10:00 PM (PST)
- **Where:** 365 Toni Stone Xing, San Francisco, CA
- **Team:** [Julaiti Alafate](https://cerebralvalley.ai/u/julaiti), [Sebastian Bosma](https://cerebralvalley.ai/u/sbosma)
- **GitHub:** https://github.com/SebastianBosma/agent_gym
- **Demo video:** https://youtu.be/GgiLPPwyugw
- **Gallery:** https://cerebralvalley.ai/e/gemini-3-hack-sf/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/gemini-3-hack-sf/hackathon/gallery/55

An automatic RL environment and RL post training tool for agents.
The tool takes a set of logs and creates a RL environment which then in turn can be used to RL post train a small model.

## More from Gemini 3 Hackathon SF

- [Linked](https://cerebralvalley.ai/e/gemini-3-hack-sf/hackathon/gallery/52)
- [FlowState](https://cerebralvalley.ai/e/gemini-3-hack-sf/hackathon/gallery/53)
- [CoPair](https://cerebralvalley.ai/e/gemini-3-hack-sf/hackathon/gallery/54)
- [Team Hackathon](https://cerebralvalley.ai/e/gemini-3-hack-sf/hackathon/gallery/56)
- [Interactive Sports Learning](https://cerebralvalley.ai/e/gemini-3-hack-sf/hackathon/gallery/57)
- [NeuroSensei](https://cerebralvalley.ai/e/gemini-3-hack-sf/hackathon/gallery/58)

---

Markdown version of https://cerebralvalley.ai/e/gemini-3-hack-sf/hackathon/gallery/55. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt