Global radar

Pinokio wrapper: installs HeartMuLa heartlib + downloads checkpoints + launches a Gradio UI for music generation.

This app lets you type a message and receive an instant reply generated by an AI language model. Simply enter your text in the chat window, and the system will respond with a coherent, context‑awar...

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

All-in-one face swapping: single photo, video, multi-source,

Background removal model developed by BRIA.AI, trained on a carefully selected dataset and is available as an open-source model for non-commercial use https://huggingface.co/spaces/briaai/BRIA-RMBG-1.4

Pinokio launcher for Higgs Audio v3 TTS with Gradio UI, SGLang-Omni backend, and automatic model download.

Contribute to Arnold2006/Jay_Caption_Beta_one_Batch_WebUI development by creating an account on GitHub.

Reconstruct 3D Gaussian Splatting worlds from video using non-rigid alignment. Supports fast and extensive modes with 2DGS/3DGS rendering. https://github.com/lukasHoel/video_to_world

ClipForge is a web-based video clipping application that allows you to create clips from your Plex media server sessions. Monitor what's currently playing, generate precise video clips with frame-accurate trimming, and manage your video collection through an intuitive web interface.

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.

Examples of ComfyUI workflows

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin993886460 (Beware of fake account)

deep hermes, but without the need for a system prompt. Autonomously responds based on its OWN judgment https://github.com/cocktailpeanut/deeperhermes

open-source coding agent

Local AI desktop app — chat, agent mode, image gen, video gen. Supports Ollama, Gemma 4, Llama, Qwen, OpenAI, Anthropic. Single .exe, no Docker.

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

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

Run Open Notebook locally via Docker with one-click install, start, and shutdown.

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