MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenario…

macOS video editor built for AI

ggml speech-to-text inference for 16+ model families

Powerful workspace management plugin, packed with features

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…

Windows / Linux desktop app built with Rust/Tauri for local Higgs Audio v3 TTS inference + local dev api through a native C++/CUDA port

Custom node for ComfyUI. A node pack to save images with metadata extracted from the input values of any node. Fork of SaveImageWithMetaData that attempts to add support for all custom nodes.

A lightweight FastAPI microservice proxy for Yahoo Finance data via yfinance, enabling seamless access for any language or platform.

TradingAgents: Multi-Agents LLM Financial Trading Framework

Unofficial ChatGPT desktop app for Linux (formerly the Codex app), built locally from OpenAI’s official macOS app. Includes Chat, Work, and Codex. Packages for Debian/Ubuntu (.deb), Fedora/openSUSE…

Telegram Desktop messaging app

A browser-based viewer for Office Open XML documents that renders to an HTML Canvas element.

LLM-powered prompt engineering node for Z-Image Turbo workflows. By Cyberdelia AI Lab.

Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

A tiling window manager for macOS based on binary space partitioning

Ultimate camera streaming application

Adaptive Test-time Learning and Autonomous Specialization

LaTeX for Visual Studio Code

A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

Truly independent web browser

Professional PostgreSQL client for NodeJS

The smallest backend framework and among the top three in the world.

Fast and accurate AI powered file content types detection

A character-level language diffusion model trained on Tiny Shakespeare

The SeedLink client library

ObsPy: A Python Toolbox for seismology/seismological observatories.

OCR & Document Extraction using vision models

Renderer for the harmony response format to be used with gpt-oss

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…