Stars
The absolute trainer to light up AI agents.
Gemma open-weight LLM library, from Google DeepMind
Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"
Chrome DevTools for coding agents
A python module to repair invalid JSON from LLMs
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
Reference PyTorch implementation and models for DINOv3
A Gaussian dense reward framework for GUI grounding training
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Your commands control the browser - made easy | Chrome Extension and RESTful API for Browser-Use
Opensource benchmark evaluating web operators/agents performance
收集全国各高校招生时不会写明，却会实实在在影响大学生活质量的要求与细节
No fortress, purely open ground. OpenManus is Coming.
A lightweight, powerful framework for multi-agent workflows
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
About Awesome things towards foundation agents. Papers / Repos / Blogs / ...
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
real time face swap and one-click video deepfake with only a single image
Official repo of Griffon series including v1(ECCV 2024), v2(ICCV 2025), G, and R, and also the RL tool Vision-R1.
[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence
Pydoll is a library for automating chromium-based browsers without a WebDriver, offering realistic interactions.
Composio equips your AI agents & LLMs with 100+ high-quality integrations via function calling
Integrate the DeepSeek API into popular softwares
A simple screen parsing tool towards pure vision based GUI agent
The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.