Ultra-minimalist macOS recording + transcription.

An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.

Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

SIA is a Self Improving AI framework to autonomously improve the performance of any AI system (Model / Agent) on a benchmark task.

Autoresearch for Go

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

Realtime speech to presentation. Let the whiteboard whiteboard itself.

cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign languag…

uBlock Origin - An efficient blocker for Chromium and Firefox. Fast and lean.

Open-Source Frontier Voice AI

On-device TTS model by Neuphonic

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal is…

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

A feed-forward 3D foundation model for reconstructing scenes from streaming data

A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.

[CVPR 2026 (Highlight)] Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

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

3D Gaussian Splat Editor

MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run direc…

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

Code for the Boxer research paper

Field Theory CLI for bookmarks, Library, commands, and agent workflows

Based on The Minimalist Entrepreneur by Sahil Lavingia

autonomous harness engineering

Clone a voice in 5 seconds to generate arbitrary speech in real-time

We write your reusable computer vision tools. 💜