App for Claude Code / Codex / Gemini / OpenCode, vibe coding anytime, anywhere

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

[CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

HY-Embodied: Embodied Foundation Models for Real-World Agents

Code for the Boxer research paper

[CVPR 2026] 4C4D: 4 Camera 4D Gaussian Splatting

The best-benchmarked open-source AI memory system. And it's free.

Offical Repository of Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding

Seoul World Model: Grounding World Simulation Models in a Real-World Metropolis

Web-based MuJoCo viewer powered by Viser

Seen2Scene takes an incomplete real-world 3D scan and generates a complete, coherent 3D scene using visibility-guided flow matching — trained directly on real-world data.

Compile agent conversations!

[CVPR 2026] Visual Geometry Transformer for Autonomous Driving

AI-powered video podcast creation skill for coding agents. Supports Bilibili & YouTube, multi-language (zh-CN/en-US), 6 TTS engines (Edge/Azure/ElevenLabs/OpenAI/Doubao/CosyVoice), 4K Remotion rend…

DVD: Deterministic Video Depth Estimation with Generative Priors

Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"

Interactive World Simulator for Robot Policy Training and Evaluation

[CVPR 2026] EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

(CVPR2026 Oral) ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

AI agents running research on single-GPU nanochat training automatically

[CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training