Statistical computation library for Rust

Language model tokenization at GB/s

XLS32 — a 32-voice polyphonic HLS/FPGA synthesizer in Google XLS (DSLX) on a Basys 3, built end-to-end with AI coding agents and verified headlessly over USB.

源内AIアプリ

A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Go framework for agentic AI app with MCP and built-in tools

Build ultra fast, tiny, and cross-platform desktop apps with Typescript.

LM Studio CLI

Minimal Claude Code alternative. Single Python file, zero dependencies, ~250 lines.

A real-time software for turn-taking, backchannel, and head-nodding prediction

Tiny AutoEncoder for Hunyuan Video (and other video models)

Massive open Japanese speech corpus

Lightweight Image Video Action Generation Inference Framework

Specification and documentation for the Model Context Protocol

Cross-platform Rust rewrite of the GNU coreutils

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

A community-maintained Python framework for creating mathematical animations.

Emote Portrait Alive - using ai to reverse engineer code from white paper. (abandoned)

The infrastructure platform for the intelligence era

Fara1.5 – A family of frontier computer use agent models

T5Voice is a lightweight PyTorch implementation of T5-based text-to-speech synthesis, supporting both streaming and non-streaming speech synthesis with zero-shot capabilities.

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

Rust GUI components for building fantastic cross-platform desktop application by using GPUI.

Training code for kokoro tts model

encrypted/remote secret manager

Drop-in replacement for Requests. Automatic HTTP/1.1, HTTP/2, and HTTP/3. WebSocket, and SSE included.