Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Sky-T1: Train your own O1 preview model within $450

Pretraining code for a large-scale depth-recurrent language model

Democratizing Reinforcement Learning for LLMs

Model Context Protocol Servers

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

😎丰富生态、🧩支持扩展、🦄多模态 - 大模型原生即时通信机器人平台 | 适配 QQ / 微信（企业微信、个人微信）/ 飞书 / 钉钉 / Discord / Telegram 等消息平台 | 支持 ChatGPT、DeepSeek、Dify、Claude、Gemini、xAI Grok、Ollama、LM Studio、阿里云百炼、火山方舟、SiliconFlow、Qwen、Moonshot…

verl: Volcano Engine Reinforcement Learning for LLMs

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

The most advanced AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

Unified framework for building enterprise RAG pipelines with small, specialized models

Make websites accessible for AI agents

Reverse Engineering: Decompiling Binary Code with Large Language Models

An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…

s1: Simple test-time scaling

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…

Build real-time multimodal AI applications 🤖🎙️📹

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Investment Research for Everyone, Everywhere.

The Magic Mask for Android

⚡ TabPFN: Foundation Model for Tabular Data ⚡

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

Command Your World with Voice

Converts text to speech in realtime