Aakash Kumar Nain

The best ChatGPT that $100 can buy.

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Building scalable models in pure JAX

Environments for LLM Reinforcement Learning