PurpleDoubleD/locally-uncensored

The all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. No Docker, no terminal, no cloud required.

What it solves

Locally Uncensored (LU) provides a single, plug-and-play desktop application that integrates multiple AI capabilities—chat, image generation, video generation, and a coding agent—into one interface. It removes the complexity of setting up local AI by eliminating the need for command-line tools, Docker, or manual configuration files, while ensuring user privacy by running 100% locally and without censorship.

How it works

LU acts as a unified studio that auto-detects and connects to 12 different local AI backends (such as Ollama, LM Studio, and vLLM). For image and video generation, it manages a bundled ComfyUI environment. The app includes a setup wizard that can install the necessary AI engines for the user, allowing them to download and run open-weight models directly through a built-in Model Manager that provides hardware-aware recommendations.

Who it’s for

It is designed for Windows and Linux users who want a comprehensive local AI suite without the technical overhead of manual installation and installation of separate tools for different modalities (text, image, video, code).

Highlights

  • Unified AI Studio: Combines uncensored chat, image and video generation, and a coding agent in one app.
  • Plug-and-Play: Auto-detects 12 local backends and offers one-click installations for AI engines.
  • Uncensored by Default: First-class support for abliterated models that answer without refusals.
  • Advanced Agentic Capabilities: Includes a coding agent with Architect mode and an Agent Mode with 28 tools and MCP support.
  • Multimodal Generation: Local image-to-image and image-to-video generation via managed ComfyUI.
  • Privacy-First: Zero telemetry, zero analytics, and works fully offline after models are downloaded.
  • Remote Access: Ability to access the local AI studio from a mobile device via LAN or Cloudflare Tunnel.

Related

  • Project
    techjarves/Uncensored-Local-Studio

    A zero-configuration, offline AI studio that integrates Stable Diffusion, LLMs, Whisper, and Kokoro TTS into a single private desktop interface with hardware acceleration.

  • Project
    Anil-matcha/Open-Generative-AI

    An unrestricted, open-source AI studio for generating images, videos, and audio using 400+ models without content filters or subscription fees.

  • Project
    Woolverine94/biniou

    A self-hosted web interface for running a wide variety of generative AI models locally, supporting text, image, audio, video, and 3D generation on hardware as basic as 8GB RAM.

  • Project
    sybil-solutions/local-studio

    Local Studio is an open‑source macOS/desktop app that lets you run, manage, and chat with self‑hosted LLM back‑ends (vLLM, SGLang, llama.cpp, MLX). It combines a Bun + Hono controller (model lifecycle, OpenAI‑compatible proxy, GPU metrics) with a Next.js/Electron UI and an integrated Pi coding‑agent. The UI works locally or can point at a remote controller, and a companion mobile app (KittyLitter) can pair to reuse the same sessions. The repo provides full dev‑setup scripts, production build instructions, and a CI‑driven release pipeline.

  • Project
    MindWorkAI/AI-Studio

    A free, lightweight desktop application that provides a unified interface for interacting with multiple LLM providers and local models using your own API keys.