Store

(BETA) AI shouldn't have a meter. Unlimited tokens. Forever. Your machine. Your agent. Use it from anywhere. Terminal-native coding agent powered by local LLMs — 100% open source, free forever, and installed with a single command. Proudly built on C#/.NET, because AI tooling should be infrastructure, not a subscription.

Contribute to PrismML-Eng/Bonsai-Image-Demo development by creating an account on GitHub.

TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion Transformer, ICLR 2026

AVTR-1: Avatars that listen back

Hy-MT2 multilingual translation — Gradio UI for 33-language translation with Hy-MT2-1.8B and Hy-MT2-7B.

SA3 medium audio inpainter — MLX SAME-L decoder + FastAPI + vanilla Svelte UI

Open singing synthesis platform / Open source UTAU successor

The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Contribute to manat0912/Avatarify-Pinokio-app development by creating an account on GitHub.

A platform for reproducible world model research and evaluation

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Real-time face swap (Decart Lucy) + voice changer (Fish Audio) fused into one app.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

AI-powered tool that automatically sorts thousands of gymnastics competition photos into folders by team and individual gymnast. Uses YOLOv8, CLIP, InsightFace, ReID and FAISS – fully offline, CUDA-accelerated.

[CVPR'26] Official code for the paper "VGG-T³: Offline Feed-Forward 3D Reconstruction at Scale"