A neuro-symbolic micro-Transformer with speculative decoding, constraint pruning, recurrent attention, and adaptive test-time scaling — built in Rust.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Official Codebase for our CVPR 2026 paper UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass

Train LLM from scratch for $5 USD - Research.

Unifying Multimodal Variational Autoencoders (VAEs) in Pytorch

🚀2.3x faster than MinIO for 4KB object payloads. RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platfor…

Make human motion capture easier.

Test-Driven Generation for Claude Code

Feed-forward model for predicting 3D physics with 3DGS + NeRF

MoCha: End-to-End Video Character Replacement without Structural Guidance

A versatile and portable proxy for capturing, manipulating, and replaying HTTP/HTTPS traffic on the go.

✨📞 Asterisk PBX in 🐳 Docker — Smallest Asterisk ever! 🚀

Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.

A unified inference and post-training framework for accelerated video generation.

Documentation and background of sign language processing

[TPAMI 2025] Official Code for "SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation"

CodeCell is a family of tiny boards that help you miniaturize your DIY robots, wearables, and IoT projects with ease! Designed for makers, each CodeCell features an Arduino-compatible ESP32 microco…

Official Repository of Absolute Zero Reasoner

yt-dlp cli bindings for Go

(ECCV 2024) SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark

⏬ Dumb downloader that scrapes the web

realtime motion tracking in blender using mediapipe and rigify

Blendshape and kinematics calculator for Mediapipe/Tensorflow.js Face, Eyes, Pose, and Finger tracking models.

Pretrained models for TensorFlow.js

Effortless Real-Time Sign Language Translation

Port of OpenAI's Whisper model in C/C++

This repo contains driver samples prepared for use with Microsoft Visual Studio and the Windows Driver Kit (WDK). It contains both Universal Windows Driver and desktop-only driver samples.

Vane is an AI-powered answering engine.