Highlights
- Pro
Stars
Qwen-CUA: Native Computer Use for (Almost) Everything — a screenshot-driven agent that operates computers with keyboard and mouse, jointly developed by the Qwen Team and XLang Lab.
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
Official Repository of "Learning to Reason under Off-Policy Guidance"
Experiment-backed reverse engineering of the macOS Codex Computer Use stack
[ICML'26] Scaling Long-Horizon LLM Agent via Context-Folding
Ongezellig archive to simplify finding official content in one repository.
EdgeBench: Unveiling scaling laws of learning from real-world environments
Train computer-use agents end-to-end on real desktops, at scale: a high-performance runtime where 8K+ live environments on one laptop thread.
Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。
Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia (ICML'26), Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)
SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles
Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction
CUA-Gym-Hub: mock web apps as reproducible RL training environments for computer-use agents
Scalable pipeline for synthesizing verifiable RLVR training data for computer-use agents
AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.
Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
Reference code for the Meta-Harness paper.
Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)