Stars
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)
verl: Volcano Engine Reinforcement Learning for LLMs
Harbor is a framework for running agent evaluations and creating and using RL environments.
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
SkyRL: A Modular Full-stack RL Library for LLMs
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A CLI to estimate inference memory requirements for Hugging Face models, written in Python.
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
Anthropic's original performance take-home, now open for you to try!
Propeller 1 design and example files to be run on FPGA boards.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Multilingual Document Layout Parsing in a Single Vision-Language Model
AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each problem, and is faster than existing implementations.
AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.
UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
Data recipes and robust infrastructure for training AI agents
Open Source Algo Trading Platform for Everyone
LLM Council works together to answer your hardest questions
"DeepTutor: AI-Powered Personalized Learning Assistant"
CVPR2024: Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
Chat language model that can use tools and interpret the results
Collaborative retina modelling across datasets and species.