Openenv

rLLM

rLLM bolts RL onto agents you already wrote. verl, trlx, OpenRLHF make you rewrite the agent into their pipeline. A deco

Gorilla

Fine-tuned models, datasets, and the Berkeley leaderboard for training and evaluating LLM API and function calling

Adaptive Engine

RLOps platform for continuously fine-tuning, evaluating and serving specialized LLMs from production feedback (company acquired by Datadog).

ART (Agent Reinforcement Trainer)

Open-source GRPO reinforcement-learning trainer for multi-step LLM agents

Diffusers

Library of pretrained diffusion models for generating images, audio, and 3D structures, for inference or training

Smolagents

Hugging Face library for agents that write their actions as Python code, with sandboxed execution

Speech To Speech

Build voice agents with open-source models