This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

Stop hunting panes. Run your AI workflow from one place.

An implementation of the Slug text rasterization algorithm in Metal

Remote Control for Codex.

Rust implementation of protobuf with editions support, JSON serialization, and zero-copy views

noq, a QUIC implementation in Rust

IP addresses break, dial keys instead. Modular networking stack in Rust.

Perfect Green Screen Keys

a simple transcription library for rust

A free, open source meeting notes app with live transcription and AI-powered note enhancement.

OpenAI compatible API servers for the Qwen3 TTS models

Rust implementation of Qwen3-ASR automatic speech recognition

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

Wolfram Language / Mathematica reimplementation in Rust (Wolfram oxidized)

π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.

Rust wrappers for libdatachannel

Lightweight coding agent that runs in your terminal

Voxtral ASR & TTS running natively and in the browser. A Rust implementation of Mistral's Voxtral mini realtime ASR / TTS using the Burn ML framework

Local AI assistant, dreaming explorable worlds.

Zero-copy hardware-accelerated video SDK for Rust (Android, iOS, Linux, macOS, Web, Windows)

Neqo, the Mozilla Firefox implementation of QUIC in Rust

Peer to Peer screen sharing framework from macOS to iPadOS, visionOS, and macOS

Official inference framework for 1-bit LLMs

💾 A library for backporting UITableView/UICollectionViewDiffableDataSource.

Generate SRT subtitle files from video using the Gladia speech-to-text API

adds momentum to the cursor on macOS