Qwen-AgentWorld: Language World Models for General Agents

Convert static images to editable PowerPoint slides — OCR, inpaint, reconstruct

Open source SDK to create applications leveraging event-based vision hardware equipment

📂 Web File Browser

The Largest World Download Project in 2b2t, and in Minecraft altogether. Full info + Renders + Timelapses (+ Torrent soon)

GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

An open-source platform for Visual AI.

[NeurIPS 2025 Spotlight] Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning.

A list of robotics companies using the Robot Operating System (ROS and ROS 2).

Official SeedVR2 Video Upscaler for ComfyUI

AI that sees your screen, listens to your conversations and tells you what to do

Heterogeneous Containerization of Agents

Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

[EMNLP 2024 Demo] TinyAgent: Function Calling at the Edge!

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

Pyodide is a Python distribution for the browser and Node.js based on WebAssembly

Powerful WASM runtime with debug capabilities

A single interface to use and evaluate different agent frameworks

Open Policy Agent WebAssembly NPM module (opa-wasm)

Testing WASM-powered AI agents

WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

XLeRobot: Practical Dual-Arm Mobile Home Robot for $660

A simple screen parsing tool towards pure vision based GUI agent

High performance (LLM-) agents execution environment with production in mind.

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

A Periodic Table of System Design Principles

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command li…