Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

Text and code embeddings research from CodeFuse: C2LLM, D2LLM, E2LLM, F2LLM

Standardized environment infrastructure for Agentic AI development.

SkyRL: A Modular Full-stack RL Library for LLMs

An Open-Source Asynchronous Coding Agent

🚀 PR Agent - The Original Open-Source PR Reviewer. This repo is not the Qodo free tier! Try the free version on our website.

Kimi K2 is the large language model series developed by Moonshot AI team

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

slime is an LLM post-training framework for RL Scaling.

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

[NeurIPS 2025] A Graph-based LLM Framework for Real-world SE Tasks

[ICML '24] R2E: Turn any GitHub Repository into a Programming Agent Environment

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

verl: Volcano Engine Reinforcement Learning for LLMs

My learning notes for ML SYS.

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Fully open reproduction of DeepSeek-R1

Efficient Triton Kernels for LLM Training

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

A generative world for general-purpose robotics & embodied AI learning.

Xiaomi Home Integration for Home Assistant

Code for the Molmo Vision-Language Model

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

[ICCV 2025, Highlight] ZIM: Zero-Shot Image Matting for Anything

Janus-Series: Unified Multimodal Understanding and Generation Models

PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

小彭老师领衔编写，现代C++的中文百科全书

Next-Token Prediction is All You Need

Official Code for ECCV 2024 paper — One-Shot Diffusion Mimicker for Handwritten Text Generation