Apps

A live 3D intelligence console for planet Earth.

MiniMax H3 omni-modal video generation in ComfyUI. Text/image/video/audio in, video with native 32kHz stereo audio out (768p default, 1080p+ supported). Disk-optimized: pruned INT8 + NVFP4 weights (~63GB instead of ~290GB). NVIDIA only.

Browse, search, and analyze sessions from Claude Code, Codex, and other coding agents locally.

A free, open-source GIS for visualizing, exploring, and analyzing geospatial data locally in your browser.

Run image generation, GGUF language models, Whisper speech recognition, and Kokoro speech synthesis locally from one offline studio.

Local multi-instrument audio-to-MIDI transcription from Kyutai and Mirelo.

An all-in-one, 100% local AI creative studio, director, and multi-track editor. Generate with MiniMax H3, LTX-2.5/2.3, Wan, Flux, Qwen, and more; turn an idea or song into a planned production; then finish it on the timeline. Requires an NVIDIA GPU (6GB+ VRAM).

Browser-based AI audio DAW for Stable Audio 3 with text-to-audio, inpainting, LoRA training, FFmpeg effects, waveform editing, sequencer, piano roll, and persistent library. https://github.com/gantasmo/stabledaw

Generate editable Ideogram JSON prompts from uploaded images.

[AMD ONLY] Super Optimized Gradio UI for AI video creation for GPU poor machines (6GB+ VRAM). Supports Wan 2.1/2.2, Qwen, Hunyuan Video, LTX Video, Flux and more. (On Windows supported by all dedicated AMD GPUs from RDNA 2 - RDNA 4)

Self-hosted AI workspace for local-first chat, agents, tools, memory, research, documents, email, and model endpoint management.

A privacy-respecting metasearch engine that runs locally.

Launcher for Stable Audio 3 Small Music, Small SFX, and NVIDIA Medium using public cocktailpeanut Hugging Face mirrors. https://github.com/Stability-AI/stable-audio-3

Expressive TTS with voice cloning, prompt-driven speech synthesis built on LTX-2.3 by Resemble AI

Tokenizer-free multilingual TTS and voice cloning with low-VRAM and VoxCPM2 Web UI/API launch modes.

Local generative video, image, and character training on Apple Silicon. Train face + voice LoRAs in-app. Q8 HQ for character clips. MLX native — no cloud, no API key.

[NVIDIA GPU REQUIRED] Realtime world generator by Overworld Waypoint world model

Minimal NVIDIA-first web app for texturing existing meshes with Hunyuan3D-2GP/mmgp while preserving rigged GLB structure when the vertex layout stays compatible.

A Python framework for AI-driven character animation using neural networks.

Strip image metadata locally in the browser.