# EvoLoRA

- **Event:** [AI Engineer World's Fair Hackathon 2026](https://cerebralvalley.ai/e/aiewf-hackathon-2026)
- **When:** Jun 27 at 9:00 AM – Jun 28 at 5:00 PM (PDT)
- **Where:** San Francisco, CA
- **Placement:** Finalist
- **Team:** [Vaibhav Satishkumar](https://cerebralvalley.ai/u/VS-Coder), [Akshay Langhani](https://cerebralvalley.ai/u/AkshayLanghani), [Pranav Emmadi](https://cerebralvalley.ai/u/PranavEmmadi)
- **GitHub:** https://github.com/Visual-Studio-Coder/EvoLoRA/
- **Demo video:** https://youtu.be/4lz4LjBrG7I
- **Gallery:** https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery/14

EvoLoRA is an auditable, bounded self-improvement loop for LoRA fine-tuning. You provide a plain-English goal; a MiniMax agent plans the evaluation set, the training data, and the LoRA hyperparameters; Python validates and controls every step; a small model is trained and scored against a locked benchmark; and the best adapter is preserved. The entire learning process is made visible: the agent plans, the model trains, results are scored and judged, and you decide whether to keep going. 

LiveKit is used for dictation support as well as narration of the training process. MongoDB is used to persist all of the training-related data and LoRA adapter paths in the cloud. Digital Ocean is used for our external LLM-as-a-judge for scoring the evals prepared by Minimax.

---

Markdown version of https://cerebralvalley.ai/e/aiewf-hackathon-2026/hackathon/gallery/14. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt