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,
What is 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.
Overview of locally-uncensored
What it is
Locally Uncensored is an all-in-one local AI studio for desktop. It provides chat, image generation, video generation, and a coding agent in a single application. It runs entirely on the user's own machine without requiring Docker, terminal usage, or cloud services. The application is free and open source under the AGPL-3.0 license. It supports Windows 10/11 and Linux (with a beta version for macOS 14 or newer on Apple Silicon).
Key features
- Chat with models that answer directly without refusals, alongside mainstream models. Supports thinking display, image upload, document indexing, voice input/output, memory across conversations, persona switching, and import of ChatGPT/Claude/Gemini exports.
- Create images and video using ComfyUI, which the app installs, starts, repairs, and updates automatically. Features include text-to-image, image editing, inpainting, background removal, video generation, image animation, clip extension, motion control, talking character, music, and Character Studio for LoRA training.
- Coding agent that shows diffs before applying changes and can perform tasks autonomously in agent mode.
- Model manager that marks which models fit the user's hardware and downloads them with one click. Works with existing engines like Ollama and LM Studio.
- Voice (beta): spoken conversation with the selected chat model, with speech recognition and voice running locally, fifteen voices available, and the model can use agent tools during conversation.
- Computer control (beta): allows a model to use the mouse and keyboard in approved applications, off by default.
Use cases
- Running a local AI assistant for chat, image generation, video creation, and coding tasks without internet dependency.
- Using AI for creative projects such as generating images, animating pictures, creating music, or training custom characters via LoRA.
- Automating desktop tasks through computer control and agent mode.
- Maintaining privacy by processing all data locally on the user's machine.
Getting started
Download the latest build from the Releases page on GitHub. Install the appropriate installer for your platform (Windows: .exe or .msi; Linux: .AppImage, .deb, or .rpm; macOS beta: .dmg). On first launch, a wizard will look for an existing AI engine and install one if needed, then set up ComfyUI. Alternatively, build from source: bash git clone https://github.com/PurpleDoubleD/locally-uncensored.git cd locally-uncensored npm install npm run dev # browser dev mode npm run tauri build # desktop binary
License and pricing
The project is licensed under AGPL-3.0 and is free and open source. Pricing type is open source.
Based on the project's public README and repository metadata.