Radar

AI investigation agent that resolves entities across corporate registries, campaign finance, lobbying, and contract data to surface non-obvious connections. Pre-built desktop app, auto-connected to Ollama.

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

Install AnimateDiff Automatic1111 Extension and the models with one click

ElevenLabs at home. Multilingual TTS with Voice Design, Voice Cloning, and end-to-end LoRA fine-tuning straight from a video or podcast. Built on VoxCPM2 by OpenBMB. 30 languages incl. Russian.

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

A live 3D intelligence console for planet Earth.

An Open Source Model for Audio Samples and Sound Design https://github.com/Stability-AI/stable-audio-tools

Controllable video-to-audio Foley (Xiaomi, ACM MM 2026)

[NVIDIA GPU ONLY] One click installer for Intel's ldm3d

[NVIDIA ONLY] a state-of-the-art open-source model for fast feedforward 3D mesh reconstruction from a single image, from Stability AI. https://huggingface.co/spaces/stabilityai/stable-fast-3d

AutoGPT is a powerful tool that lets you create and run intelligent agents https://github.com/Significant-Gravitas/AutoGPT

Automatically clip videos and generate captions for LoRA training using advanced vision models like Gemma-3, Qwen3-VL, and Qwen2-VL.

One-click shorts: niche ideas, script, voiceover, footage, captions and a finished video in 9:16, 16:9, 1:1 or a custom size. Optional photo-to-3D module.

LivePortrait - img2vid only: 6GB VRAM & ~8GB download

Describe any song in plain English, compose a structured caption and lyrics locally, and generate it with MiniMax Music 3.

A live 3D intelligence console for planet Earth.

An all-in-one, 100% local AI video, image, music & 3D studio. Its Director mode turns a single prompt into a full music video or short film — LLM-planned, shot by shot. Includes native Hunyuan3D generation alongside WanGP models. Requires an NVIDIA GPU (6GB+ VRAM).

Bolt.new: AI-Powered Full-Stack Web Development in the Browser -- for Pinokio

Massively Multilingual Speech (MMS): Persian Text-to-Speech

Local-first AI video editor with optional native MiniMax H3 generation on Apple Silicon.