Stars
Scalable toolkit for efficient model reinforcement
🙌 OpenHands: AI-Driven Development
A Multi-Policy, Multi-Agent RL Training Framework
Machine Learning and Computer Vision Engineer - Technical Interview Questions
🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.
A self-hosted ML coding practice platform. 68 problems from ReLU to flow matching — attention, training, RLHF, diffusion, and more. Instant feedback in the browser.
See your claude code logs in clear details in your dashboard
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
⛽️「算法通关手册」：从零开始的「算法与数据结构」学习教程，200 道「算法面试热门题目」，1000+ 道「LeetCode 题目解析」，持续更新中！
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
A very simple GRPO implement for reproducing r1-like LLM thinking.
A unified framework for building agentic RL environments.
SGLang model provider for Strands Agents.
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Our library for RL environments + evals
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, sc…
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
[ICML 2026] Decoding Tree Sketching (DTS): a training-free & model agonistic & plug-in framework for LLM parallel reasoning.
AdalFlow: The library to build & auto-optimize LLM applications.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
slime is an LLM post-training framework for RL Scaling.
how to optimize some algorithm in cuda.
DeepEP: an efficient expert-parallel communication library