Stars
[SIGGRAPH ASIA 2026]: End-to-End Motion Capture for Arbitrary Skeletons
The batteries included agent harness.
Parallelized, coverage-guided, mutational Solidity smart contract fuzzing, powered by go-ethereum
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
AirPods liberated from Apple's ecosystem.
Building a Secure and Interoperable Future for AI-Driven Payments.
Kitten TTS web demo using tansformers.js
Text-audio foundation model from Boson AI
An open-source AI agent that brings the power of Gemini directly into your terminal.
The open-source CapCut alternative
OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871
WHIR 🌪️: Reed–Solomon Proximity Testing with Super-Fast Verification
C++ implementation of the Antelope protocol with Savanna consensus
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!
Cassowary/JS, better, faster, future-ready
learn LLM inference on Apple Silicon for systems engineers: build a tiny vLLM + Qwen
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Lightweight coding agent that runs in your terminal
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
High-performance In-browser LLM Inference Engine
[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from sim…