Global radar

Free, local-first evaluation dashboard for agent CLIs with cross-harness transcript collection, live trace intelligence, deterministic graders, and accuracy audits.

Convert your videos to densepose and use it on MagicAnimate https://github.com/Flode-Labs/vid2densepose

A visual node-based testing harness for AutoGen multi-agent experiments

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

AI Song Generation with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model. [NVIDIA ONLY]

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

Pinokio launcher for the currently open-sourced HY-World 2.0 WorldMirror 2.0 reconstruction demo.

Upload a picture or select a sample, and the app creates resized versions that fit preset token budgets (70, 140, 280, 560, 1120). It preserves the original aspect ratio and shows the new dimension...

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

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

The open-source CapCut alternative

Ultra-lightweight text-to-speech (15M-80M params) — CPU optimized, 8 voices, ONNX-powered

✂️ Open-source, self-hosted Opus Clip alternative. Turn long YouTube videos or uploads into viral 9:16 vertical shorts: AI viral-moment detection (Gemini), auto transcription + subtitles, active-speaker reframing, in-browser editing, and one-click TikTok / Reels / Shorts scheduling.

Simple Qwen3-VL gguf model loader for Comfy-UI.

This app lets you upload a photo and replace the face with a new one generated by AI. You just need to provide an image and describe what you want the new face to look like. The app will create a r...

Video to Openpose & DWPose (All OS supported) https://github.com/sdbds/vid2pose

Discover amazing ML apps made by the community

an ai avatar creator with lip sync.

:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)