Starred repositories
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Production ready toolkit to run AI locally
NexRL is an ultra-loosely-coupled LLM post-training framework.
An End-to-End Infrastructure for Training and Evaluating Various LLM Agents
USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
[FSE'2026] SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
A simple yet powerful agent framework that delivers with open-source models
OpenCUA: Open Foundations for Computer-Use Agents
Renderer for the harmony response format to be used with gpt-oss
Official repo of Toucan: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
A General, Accurate, Long-Horizon, and Efficient Mobile Agent driven by Multimodal Foundation Models
Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environment…
AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.
A PyTorch native platform for training generative AI models
PyTorch native quantization and sparsity for training and inference
slime is an LLM post-training framework for RL Scaling.
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
A curated list of papers related to constrained decoding of LLM, along with their relevant code and resources.
Train your Agent model via our easy and efficient framework
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
SGLang is a high-performance serving framework for large language models and multimodal models.
Building Open LLM Web Agents with Self-Evolving Online Curriculum RL
MineRL Competition for Sample Efficient Reinforcement Learning - Python Package
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
Model Context Protocol Servers
Space-filling curve for rectangular domains or arbitrary size.