Stars
Stable and Efficient Reinforcement Learning for Trillion-Parameter LLMs
GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.
Evaluate and improve models and agents using environments
The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Me…
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
Official Implementation of VGG-Flow (NeurIPS 2025; https://arxiv.org/abs/2512.05116)
AI agents running research on single-GPU nanochat training automatically
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
DigitalPlat FreeDomain: Free Domain For Everyone
[AISTATS 2025] Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector
This is the code repo for the paper VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models (CVPR 2025).
🚀 One-stop solution for creating your AI twin from chat history 💡 Fine-tune LLMs with your chat logs to capture your unique style, then bind to a chatbot to bring your digital self to life.
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
Official Implementation of Nabla-GFlowNet (ICLR 2025)
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
A Text-guided Protein Design Framework, Nat Mach Intell 2025 (https://www.nature.com/articles/s42256-025-01011-z)
Cayman is a Jekyll theme for GitHub Pages
Website for the Table Representation Learning workshop (TRL).
A Zola theme for hosting academic workshops and seminar series
A comprehensive guide on how to create beautiful scientific figures for technical publications, presentations, and posters
A high-throughput and memory-efficient inference and serving engine for LLMs