Radar

🐍 | Python library for Runpod API and serverless worker SDK.

Realtime streaming TTS demo using microsoft/VibeVoice-Realtime-0.5B

MLX-native TRELLIS.2 inference for Apple Silicon — generate 3D meshes from images on > 16GB Macs

Control browsers

Official browser 3D editor: Three.js, Svelte, collaboration and optional AI.

One-click launcher for Stable Diffusion web UI (AUTOMATIC1111/stable-diffusion-webui)

Open-source (Apache-2.0) orchestrator for Claude Code, Codex & 30+ coding agents. Plan, run and supervise agent teams from task to merged PR. Desktop (macOS, Windows, Linux) + iPhone & Android apps.

State-of-the-art 1B OCR model (83.2% on OlmOCR-Bench). Local version of the HuggingFace demo. Created by Claude Code, orchestrated by TheAwakenOne.

User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs https://github.com/open-webui/open-webui

A pinokio script for https://github.com/microsoft/TRELLIS

Video restoration tool

i have patched and reengineered open sora to work on windows

A lightweight local launcher and control panel for llama.cpp.

[NVIDIA ONLY] AllTalk-TTS is a unified UI for E5-TTS, XTTS, Vite TTS, Piper TTS, Parler TTS and RVC, based on CoquiTTS, including a finetune mode.

An input that becomes what you mean: one text box that morphs into the right UI as you type. Powered by TypeSafe Jev, works offline.

Local-first AI music generation studio powered by ACE-Step 1.5.

A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects

A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects

Paste long text, clean it into readable sections, summarize each section, and ask questions in-browser with WebGPU. Choose between LFM2.5 230M, 350M, 1.2B-Instruct, and 1.2B-Thinking.