The plug-and-play local AI studio·Chat · Code · Image · Video · Remote
WINDOWS · ~14 MB installer · AGPL-3.0
Real AI on your own computer. One installer, no command line, no Docker — private, free, and yours. In local mode: no account, no cloud, nobody watching.
What you can do
Ask anything. No limits, no sign-up, no one reading along. Show it a photo, drop in a PDF, and it remembers what matters across chats. You don't pick the tech — the app finds and installs the right free AI for you. You just type.
Tell it what you want in plain words. It opens your files, makes the changes, runs the steps, and shows its work as it goes. Great for small fixes, quick scripts, and “why is this broken?” — no separate coding app needed.
Type what you imagine and get a picture. Turn a photo into a short video. It's all built in — no plugins to wire up, no confusing setup. The app installs each tool for you with one click.
Your PC does the heavy lifting; your phone is just the remote. Scan a QR code, type a 6-digit code, and the whole thing — chat, coding, tools — is in your pocket, from anywhere.
New in 2.6.9
2.6.9 puts the top bar and the Create toolbar back to the 2.6.7 layout after feedback on Discord, opens the context size menu in full, and lets Linux installs from the AUR or unpacked by hand update again. Underneath it is 2.6.8: a long conversation folds its older turns into a summary instead of running out of room, an agent hands work to background agents that run while you carry on, a reasoning model gets a dial for how much thinking a reply may pay for, every local model answers on one OpenAI-compatible address, and the built-in engine has a name of its own, the LU Engine. Out now for Windows and Linux, free as always, and the app updates itself.
Type /compact and the older turns are folded into a summary the chat model writes itself, in the language of the conversation, while the recent turns stay as they are. Auto-compact is opt-in and announces itself every time it fires, and a second compaction keeps the first.
In Agent and Code mode the agent hands a self-contained task to a sub-agent that works while you carry on. A panel on the right shows what is running, the main agent is woken when one finishes, and delegating asks no extra question: a sub-agent inherits the permissions of the run that started it.
Low, Medium and High sit beside the Think button, with Max on GLM 5.3, and they decide how many tokens a reply may spend on thinking. GLM 5.3 (Pro) and GLM 5.3 Flash (Hosted) joined the cloud catalogue, and the cloud model list keeps one fixed order.
Settings, Local API starts an OpenAI-compatible server on your machine that lists every model from the LU Engine, Ollama and LM Studio under one address, so any tool that talks to OpenAI can talk to your own machine. Localhost by default, LAN if you allow it, always behind a token.
It moves to a free port when 8127 is taken and retries once after a start that fails. A chat model you downloaded stays visible as Installed even while the engine is off, its tile has a Use button that starts the engine and loads it, and your own model folder is read, four levels deep.
AMD on Windows is read from the HIP SDK, AMD on Linux reports its memory without ROCm, the deb and the rpm name libvulkan1 and libgomp1, the ComfyUI installer checks the environment it built, the Character Studio setup picks a Python it can use and clears its own dead ends on the way to a finished character, and the Mac stopped asking for your music library at first launch. Three uncensored models joined the catalogue, and Ctrl+K opens a command palette.
Why
In local mode your chats never leave your computer. No subscription, no tracking, no limits — and no company reading along. Most local-AI apps stop at text chat; this one gives you chat, code, images, and video in one place, and your phone can run it from anywhere.
It's free and open source — anyone can check the code. Local wins for privacy and unlimited use; when you want a cloud model for the really hard stuff, you can plug your own in. Tested with 2,200+ automated checks so it just works.
Setup
No tech skills needed. No command line, no setup files — just install it like any normal app and you're chatting in minutes.
One file. Click it and install like any app. It keeps itself up to date. Free, forever.
On first start it checks what you've already got and sets it up for you. Nothing installed yet? It grabs the free AI engine for you in one click.
Pick an AI and start typing. Flip to coding, or to images and video, whenever you like. Want to add a cloud account later? One setting.
Models
Whatever you want to do — chat, make art, make videos — there's a free AI for it. The app installs them for you and only suggests the ones your computer can run. The big names are all here: Qwen, GPT-OSS, Llama 4, Gemma 4, DeepSeek and more.
Google's free chat AI. It can read your pictures too, and the small version runs on a basic PC.
The smart ones — best for thinking through tough questions and writing code. Uncensored versions included that just answer, no lectures.
A crowd favourite for photo-real images. Make a picture from words, or remix one you already have.
Truly uncensored, no filters — about 10 seconds per image.
Turn a sentence into a video clip. Quick, and works on regular hardware.
Got a picture? Turn it into a moving video. Runs on most laptops with a graphics card.
Writing
Plain-English guides to running AI on your own PC — what to install, what runs on your machine, and how it compares to the rest.
No command line, no Docker. One installer, one-click models, honest hardware requirements.
ComparisonLocally Uncensored, Jan, Ollama, Open WebUI, GPT4All, Msty, KoboldCpp — compared honestly.
BeginnerFLUX and SDXL quality on your GPU without touching a ComfyUI node graph.
GuideYour PC runs the model, your phone is the remote. Private, free, no APK needed.
GuideReal GGUF sizes, the VRAM math for 12 GB and 24 GB cards, the chat template trap, vision setup.
GuideQwen 3.6, Gemma 4 Heretic, Llama 3.1, Hermes 3. What abliteration is, where to download.
ReleaseSingle-instance lock, configurable HuggingFace path, in-app Privacy section, Linux drag fix.
GuideAll sizes from E4B to 27B. Native tools, vision, uncensored variants.
GuideUpload a photo and turn it into something new. Powered by FLUX, Z-Image, SDXL.
ComparisonComplete comparison of GPT4All, Open WebUI, LM Studio, Jan, and more.
GuideSetup guide. Models, hardware, and why local beats cloud.
VersusBoth open source. Only one does chat + code + images + video.
VersusOpen source all-in-one vs polished closed-source chat client.
GuideHow LU handles ComfyUI setup, models, and workflows automatically.
GuideWan 2.1, HunyuanVideo, LTX, FramePack. Hardware requirements, model picks.
Questions
A free, open-source local AI studio for your desktop. Install it like any normal app and you're chatting, generating images, and making videos in minutes — no command line, no Docker, no cloud. Under the hood: chat with 20+ provider presets, a coding agent, image generation via ComfyUI (FLUX 2, Juggernaut XL, Z-Image, SDXL), and video generation (Wan 2.1, HunyuanVideo, LTX 2.3, FramePack F1) in one interface. AGPL-3.0 licensed.
Yes. Qwen 3.8 27B is in the Model Manager since v2.6.6, and vision works: the image tower comes as a separate mmproj file that the download writes next to the model. Official, abliterated and uncensored builds, plus a 9B distill for small cards. GPT-OSS-120B and GPT-OSS-20B run via Ollama. GLM-4.7 Flash supported through Ollama. Also ready: DeepSeek R1, Llama 4, Gemma 4, Mistral Small 3, Phi 4.
Yes. Locally Uncensored works as a ChatGPT and Claude alternative that runs on your own hardware. Use Qwen 3.8, GPT-OSS, GLM-4.7, DeepSeek R1, Llama 4 or Gemma 4 instead, or add cloud providers (OpenAI, Anthropic, OpenRouter, Groq) alongside the local stack.
Yes. After setup and model download, no internet is needed for the local providers. No accounts, no telemetry, no usage limits. Cloud providers are optional — the core runs one-hundred percent on your hardware.
Those tools handle text chat. Locally Uncensored adds a coding agent with fourteen MCP tools, image generation, video creation, A/B model comparison, local benchmarking, granular permissions, file upload with vision, and thinking mode — all in one app.
Text chat: 8 GB RAM. Image generation: NVIDIA GPU with 8+ GB VRAM. Video generation: 10-12 GB VRAM. The app auto-detects hardware and recommends models. Windows 10/11 and Linux supported.
Abliterated models with artificial restrictions removed. The AI responds honestly without refusing or adding disclaimers. Combined with local execution, your conversations stay private.
Only if you explicitly dispatch a chat over LAN or Cloudflare Tunnel. Remote is opt-in, gated behind a six-digit passcode, and you see exactly when a device is connected. No background uploads. No telemetry.
Not yet. Windows and Linux for now. macOS support is on the roadmap but not promised. The source is AGPL-3.0 if you want to build for your platform.
WINDOWS · ~14 MB installer · AGPL-3.0 · 100% open source