PrimeIntellect-ai/prime-envs

Standardized environment infrastructure for Agentic AI development.

An interface library for RL post training with environments.

Build RL environments for any domain from real cases that Browser Use agents mine from the web

Evaluate and improve models and agents using environments

Research infra for creating RL environments, post-training, and evals.

💻 SETA: Scaling Environments for Terminal Agents

Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.

The official paper for EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL.

A toolkit for developing and comparing reinforcement learning algorithms.