Wanted

Video translation and dubbing tool powered by LLMs. The video translator offers 100 language translations and one-click full-process deployment. The video translation output is optimized for platforms like YouTube，TikTok. AI视频翻译配音工具，100种语言双向翻译，一键部署全流程，可以生抖音，小红书，哔哩哔哩，视频号，TikTok，Youtube等形态的内容成适配

Convert 2D videos to 3D VR format using AI depth estimation.

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Official code for "Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis"

Agentic AI Infrastructure for magnifying HUMAN capabilities.

Perplexica is an AI-powered answering engine.

A lightweight, powerful framework for multi-agent workflows

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

JARVIS - A ASSISTANT WHICH IS NEEDED FOR EVERYONE

AuraCore: a local-first web UI for LLM chat + SDXL image generation + image editing, with pluggable backends and Pinokio compatibility.

Contribute to kijai/ComfyUI-MMAudio development by creating an account on GitHub.

Neuro-Sama style AI Companion, utilizing a WebUI created by Google Stitch.

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

Open-source alternative to OpusClip - AI-powered YouTube Shorts generator.
100% free and unlimited.

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

Audio driven talkinghead generation based on LivePortrait.

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

SkyReels V1: The first and most advanced open-source human-centric video foundation model

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement