[opensourcedex]

locally-uncensored is a free, open source ai interaction & interfaces project written in TypeScript and released under AGPL-3.0. It has 1,679 GitHub stars, 261 forks and 7 open issues, and was last pushed 4 days ago. On this registry it ranks #66 of 76 tracked projects in AI Interaction & Interfaces, with 5 head-to-head comparisons available. It gained 29 stars over the last 3 tracked days.

What is locally-uncensored?

What it is

Locally Uncensored is a free, open source desktop AI studio built in TypeScript and released under AGPL-3.0. It brings chat, image generation, video generation, a coding agent, and agent mode into one Windows and Linux application. The project lives in the local AI ecosystem, where users run models on their own hardware instead of sending prompts to a cloud service.

It solves the friction of assembling a local AI workflow. Instead of installing separate engines, managing model files, writing terminal commands, or configuring Docker, the app provides installers, a first-launch wizard, and a model manager. It can detect or install an AI engine and ComfyUI, mark models that fit the hardware, download them, and link models already stored by Ollama or LM Studio. The result is one window with Chat, Create, Code, and Agent tabs, so users can switch tasks while keeping the same models.

Key capabilities

  • The application runs chat, image creation, video creation, coding agent work, and agent mode in one desktop window.
  • The first-launch wizard finds or installs an AI engine, then does the same for ComfyUI.
  • The model manager marks hardware-compatible models, downloads them, and links existing Ollama or LM Studio files.
  • The chat interface shows model thinking as it happens and offers an effort control on models that provide one.
  • The app supports image upload, document chat through a local index, and a coding agent that shows a diff before changes are applied.

Who uses it and how

  • Desktop users who want local chat and media generation install Windows .exe or .msi files, or Linux .deb, .rpm, and .AppImage packages.
  • Developers use the Code tab and coding agent to review diffs before applying changes, while using the same local model as chat.
  • Existing Ollama or LM Studio users connect stored models through the model manager, avoiding duplicate downloads and extra setup.

Getting started

Users install the latest release from GitHub Releases as .exe or .msi on Windows, or .deb, .rpm, or .AppImage on Linux; source builds use git clone, npm install, npm run dev, and npm run tauri build.

When to use it — and when not to

Choose it when the goal is a local desktop workflow on Windows or Linux without Docker, terminal setup, or cloud dependency. Avoid it when macOS is required, because no macOS installer is provided and source builds are the only route. The project is new, with a zero-year repository age and limited contributor data, and unsigned NSIS installers may trigger false-positive antivirus warnings.

project readme (upstream, from github) — read inline

Locally Uncensored

The all-in-one local AI studio for your desktop. Chat, images, video and a coding agent in one app. Install it, pick a model, go.

Free, open source, Windows and Linux. Everything runs on your own machine. No Docker, no terminal, no config files.

License: AGPL v3 GitHub stars GitHub last commit GitHub Discussions Discord Website

Download · Three steps · What is in the box · How it compares · Models · FAQ

Chat that draws your images Images and video in the same window
Chat Create
The coding agent shows the diff first Agent mode does the legwork
Coding agent Agent mode

Download

Take the latest build from Releases.

Platform File Status
Windows 10 and 11 .exe (NSIS, recommended) or .msi Tested every release, signed auto update channel
Linux .deb, .rpm or .AppImage Built on every release
macOS none yet Builds from source with npm run tauri build

Some antivirus engines flag unsigned NSIS installers that download other binaries, which is a false positive. The installer is built by GitHub Actions from the public source on master, and the update channel is signed against a public minisign key, so you can verify both: see SECURITY.md.

Current release: v2.6.9 (September 2026). Every change since 1.0.0 is in CHANGELOG.md.

Three steps

  1. Install. Run the installer like any other program. On first launch a wizard looks for an AI engine that is already running on your machine, and installs one for you with a single click if there is none. It does the same for ComfyUI, which draws the images and video.
  2. Pick a model. The model manager marks which models fit your hardware and downloads them in one click. It works with the engine you already have (Ollama, LM Studio and others) and can link models those tools already store, without copying them.
  3. Create. Chat, Create, Code and Agent are tabs in one window. Type in one, switch to the next, keep the same models.

Walkthrough with screenshots: Getting started guide. New to local AI: the five minute beginner guide.

Build from source, or contribute
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

setup.bat on Windows and setup.sh on Linux and macOS bootstrap Node, Git and Ollama for dev mode. See the contributing guide.

What is in the box

Chat. Models that answer directly, without refusals, next to the mainstream ones in the same menu. Thinking is shown as it happens, with an effort control on the models that offer one. Upload an image and ask about it, chat with your own documents through a local index, talk instead of typing and have answers read back, keep a memory across conversations, switch personas, and import your ChatGPT, Claude or Gemini export so the old threads come with you. A long conversation folds its older turns into a summary instead of running out of room.

Create. Images and video on your own GPU through a ComfyUI the app installs, starts, repairs and updates for you. No node graphs. The lanes are text to image, edit and image to image with a mask for inpainting, remove background, video, animate an image, extend a clip, motion control, talking character, music, and Character Studio, which trains a character on your own card and drops it into your local LoRA folder. A LoRA picker with a stack and strength sliders reads the folder live, and everything you make lands in the gallery. Upscale and Erase Object are the two lanes that run in the cloud only. How it works.

Code. A coding agent that builds a map of the repo, edits only the lines you asked for, shows the diff before it applies anything, runs your tests and reads the failures, and carries typed git tools and per project rules in a .lurules file. Ask, Plan and Bypass modes per conversation, a file explorer with preview, and a workspace per project. A Local API in Settings puts every local model on one OpenAI compatible address behind a token, so your other coding tools can use the same machine.

Agent. Web search and fetch, reading and writing files, a shell, code execution, screenshots, image and video generation, and your own MCP servers on top. Long jobs go to background agents that work while you carry on, and a panel shows what is running. Every tool call passes a permission gate you control, and a read only run stays read only.

Everywhere. Reach the app from your phone over your LAN or through a Cloudflare tunnel, paired by QR code and a passcode, off until you turn it on, with connected devices listed. Compare two models side by side, benchmark them on your own hardware for speed, cost and correctness, and take updates over a signed channel. Phone details.

Optional: LU Labs Cloud

Some models are larger than any desktop card. Flip the Cloud switch in the same app and those run on hosted GPUs instead, with the heavy Create lanes alongside them. The same account works in the browser at lu-labs.ai, on a plan or on credit packs that do not expire. The local app stays free either way, and switching back to local costs nothing: plans and prices.

How it compares

Locally Uncensored Open WebUI LM Studio Jan SillyTavern
Chat Yes Yes Yes Yes Yes
Image generation Yes No No No Partial
Video generation Yes No No No No
Image to image and image to video Yes No No No No
Coding agent Yes No No No No
Agent with tools and MCP Yes No No No No
Works out of the box Yes No Yes Yes No
Remote access from your phone Yes Partial No No Partial
Compare and benchmark Yes No No No No
Answers directly, without refusals Yes No No No Partial
Voice in and out Yes Partial No No Partial
Document chat Yes Yes No No No
Runs without Docker Yes No Yes Yes Yes
Open source Yes Yes No Yes Yes

Deep dives: vs LM Studio · vs Jan · vs Open WebUI · vs GPT4All · vs Msty · vs KoboldCpp · vs SillyTavern · LM Studio alternatives · Best local AI apps 2026

Models that run well

The model manager holds the full catalog and marks what fits your machine. These are the ones worth starting with.

Text

| Model | Download | Notes | |-------|----------

readme truncated — read the full docs on github

Frequently asked questions

Is locally-uncensored free to use?

locally-uncensored is open source under the AGPL-3.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does locally-uncensored do?

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 written in?

locally-uncensored is primarily written in TypeScript. Its source is publicly available at https://github.com/PurpleDoubleD/locally-uncensored, and it has 1,679 GitHub stars.