Starred repositories
Code for "SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes"
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
A claude code skill to delegate prompts to codex
Streaming speech recognition running natively and in the browser. A pure Rust implementation of Mistral's Voxtral Mini 4B Realtime model using the Burn ML framework.
JAGS' batteries-included Claude Code SDLC config.
Pure C inference of Mistral Voxtral Realtime 4B speech to text model
Deep Agents is an agent harness built on langchain and langgraph. Deep Agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped…
[ICLR 2026] FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion
Deep knowledge retrieval for Obsidian, completely offline.
Official Repo for Fast-SAM3D: 3Dfy Anything in Images but Faster
AceForge is a local-first AI music workstation for Apple/OSX based on Ace-Step, DeMucs, XTTSv2
Highly accurate and efficient VSLAM system for Python
Official repository for the paper "Audio ControlNet for Fine-Grained Audio Generation and Editing".
[SiggraphAsia25] OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models
Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)
Aggressive decode optimizations for Qwen3-0.6B on RTX 5090
Generate beautiful procedural clouds in Three.js using WebGPU raymarching with WebGL2 billboard/mesh fallbacks.
Room Envelopes layout dataset generation code
This is the official repo of paper: Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation
AI powered open source recommender system engine supports classical/LLM rankers and multimodal content via embedding
Public documentation, standards, and knowledge base for the Sigma Stratum research program and the Sigma Runtime architecture. Includes SRD, SRS (SRIPs), governance, legal, and all related technica…
A reading companion app for iOS that lets you capture thoughts, quotes, and insights as you read — using your voice, camera, or keyboard.
Collaborative 3D Modeling Application on the Web
Roboto_origin Fully Open-Source DIY Humanoid Robot/萝博头原型机全开源手搓级人形机器人