Search Packages

judgeval

The open source post-building layer for agents. Our environment data and evals power agent post-training (RL, SFT) and monitoring.

ms-swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

hud-python

OSS RL environment + evals toolkit

learnlens-rl

Universal evaluation layer for OpenEnv agentic RL environments. Measures what an agent learned - not just how much reward it accumulated.

learnlens

Universal evaluation layer for OpenEnv agentic RL environments. Measures what an agent learned - not just how much reward it accumulated.

oat-llm

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

textpolicy

Reinforcement learning for text generation on MLX (Apple Silicon)

oxrl

A lightweight post-training framework for LLMs and VLMs

r-torch

An open source implementation of R1

toolbrain

A framework for agentic tool use training with reinforcement learning

lightrft

Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework

mlx-guided-grpo

Train reasoning models on your Mac. GRPO training framework for Apple Silicon with curriculum learning.

genteki-hdp

OSS RL environment + evals toolkit

open-parl

PARL (Parallel-Agent Reinforcement Learning) - A training paradigm for coordinating multiple agents in parallel workflows