Avernus API server and client for LLM, SDXL, FLUX, Qwen-Image, WAN, and Ace-Step inference and many other architectures.

Package JVM applications (Clojure, Java) into self-contained binaries. No JVM installation required to run the output.

Webbased old-school Amiga music tracker in plain old javascript - Plays and edits Amiga Mod files and FastTracker XM files

AceForge is a local-first AI music workstation for Apple/OSX based on Ace-Step

Build GUI for your Python program with JavaScript, HTML, and CSS

Fast, light framework to build your desktop and mobile apps

Fusio provides file operations on multiple storages across various async runtimes.

Playwright MCP server

Nodes for high resolution outputs and high frame numbers using LTX-2 in ComfyUI

Kubectl plugin to ease sniffing on kubernetes pods using tcpdump and wireshark

🍎 Rhythm game about cutting apples

(WIP) Fully playable, open source recreation of every Rhythm Heaven minigame with a built in level editor.

🔥 Clone and recreate any website as a modern React app in seconds

Experimental node-based UI for Strudel built with React Flow.

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Observability data lake engine

Talk to Ava, an AI assistant running entirely in your browser. Private and no server required.

Remove backgrounds from images directly in the browser environment with ease and no additional costs or privacy concerns. Explore an interactive demo.

Simple building blocks for protobuf marshaling and unmarshaling

The package to wrap Aiport server implementation (DuckDB Airport Extension)

A ComfyUI node pack that implements FreeLong (NeurIPS 2024) spectral blending for Wan 2.2 video generation

ComfyUI for Audio

Candy Dungeon Music Forge (CDMF) is a local-first AI music workstation for Windows. It runs on your PC, uses your GPU, and keeps your prompts and audio on your hardware. CDMF is powered by ACE-Step…

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 t…

We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference speed.

MLX version of z-image model

Experimental proof-of-concept for opensensor.space demonstrating how to generate Snappy-compressed Parquet files directly on an ESP32-S3 and upload them to AWS S3.