Write HTML. Render video. Built for agents.

You built it. Now brag. Turn the project you just created into a short, shareable launch video with one command.

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows, iOS testflight! Android, Linux waitlist open! A local Wispr Flow alternative. Follow https:…

Orchestrate Claude, Codex and Grok in one app. Open-source (MIT), reuses the subscriptions you already pay for.

Automatically Saw Large PRs into Smaller Stacked PRs

🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.

It do a thing

A framework for Claude Opus to intelligently orchestrate subagents.

A collection of standardized JSON descriptors for Large Language Model (LLM) files.

A framework to enable a multimodal model to operate a computer.

The official Python library for the OpenAI API

Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

A repository for log-time feedforward networks

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

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

Python bindings for llama.cpp

Continuous Integration for LLM powered applications

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

Draw / find polygons fast without opencv, useful in machine learning pipelines.

Scenic: A Jax Library for Computer Vision Research and Beyond

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

A guidance language for controlling large language models.

HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels

Supercharge Your LLM Application Evaluations 🚀

A PyTorch-based Speech Toolkit

We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multi…

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Unofficial PyTorch implementation of Google AI's VoiceFilter system