Stars
Agentic RL on Any Harness at Scale
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
A construction kit for reinforcement learning environment management.
NexRL is an ultra-loosely-coupled LLM post-training framework.
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.
A project implementing various agentic RL based on the Slime post-training framework
[COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
Evaluate and improve models and agents using environments
Standardized environment infrastructure for Agentic AI development.
Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
Docker image registry for SWE-bench, created by Epoch AI.
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
SGLang is a high-performance serving framework for large language models and multimodal models.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
slime is an LLM post-training framework for RL Scaling.
Magnificent app which corrects your previous console command.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
The agent that grows with you
Flutter makes it easy and fast to build beautiful apps for mobile and beyond
A framework for building native applications using React
AndroidWorld is an environment and benchmark for autonomous agents
MAI-UI: Real-World Centric Foundation GUI Agents ranging from 2B to 235B
Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀