Prompt, run, edit, and deploy full-stack web applications using any LLM you want!

🤖 Open-source crypto trading bot | 📈 DCA & GRID strategies | ✨ UI | ⭐ Star to support the project!

lossy video compression challenge

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

The repository is refreshed every hour and offers categorized, ready-to-use text and config files for both developers and general users.

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

Ground Station is all-in-one satellite monitoring suite

AI agents running research on single-GPU nanochat training automatically

Time Series Transformer for Crop Modeling

Anthropic's Interactive Prompt Engineering Tutorial

PDF Parsing for RAG — Convert to Markdown & JSON, Fast, Local, No GPU

The official Postman collection for the Tomorrow.io API

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images

[AAAI 2026] MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

[CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

[ICCV 2025 Highlight] Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

[3DV 2026] VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

From video file to a 3D object via NeRF - project is based on instant-ngp

Generate 3D objects conditioned on text or images

Text-To-3D dream-fusion

VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control

Research code accompanying AlphaGenome

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.

Official implementation of "VideoMaMa: Mask-Guided Video Matting via Generative Prior"

VIGA: Vision-as-Inverse-Graphics Agent