A private ChatGPT-style assistant on your own PC. Download, open it, click Easy Setup, and start chatting. No account or API key needed for local models. See the privacy details below.
Image generation, roleplay, voice, and small games on your own graphics card. Download, open it, click Easy Setup, and it installs the image model for you. No Python, no account.
A real browser your agent can drive: REST API on port 3000, a built-in MCP server, WebDriver on 9515, CDP on 9222. Download below, or skip to the command-line and Docker options.
Already run LM Studio, Ollama or ComfyUI? Easy Setup adopts the GGUFs you have by hardlink, runs on llama.cpp and stable-diffusion.cpp, and decides whether chat and images share the card or take turns. What you keep and what changes.
Every knob is in the same free download: placement modes, runtimes, quants, tensor split, MoE offload, distributed GPUs. Install below, then open the Setup tab. Advanced page.
| System | File | Size |
|---|---|---|
| Windows 10 / 11 (64-bit) | Installer (.exe)LumaBrowser Setup 1.8.0.exe | |
| Windows portable | Portable (.exe, no install)LumaBrowser-1.8.0-portable.exe | |
| macOS, Apple Silicon (M1 to M4) | App bundle (.zip)LumaBrowser-1.8.1-arm64-mac.zip | |
| Linux (x86-64) | AppImageLumaBrowser-1.8.0.AppImage |
Each installer is a normal desktop app. The only speed bumps are the ones every unsigned download hits, and they take one click each. Then the first-run guide takes over.
LumaBrowser Setup 1.8.1.exe.%LOCALAPPDATA%\LumaBrowser; you can move that folder later from Settings.Some antivirus products flag new, unsigned installers on sight. If yours quarantines the file, restore it and add an exception for the LumaBrowser folder. The app sends version check-ins and, when you use Template Builder, generalized page templates. Read the privacy policy.
The portable build is a single .exe you can run from any folder, including a USB stick. It keeps its data next to the standard location.
The macOS download is a .zip, not a disk image, and it is built for Apple Silicon (M1 or later). Intel Macs are not supported from 1.8 onward.
.zip in Downloads. It unpacks to LumaBrowser.app.LumaBrowser.app into your Applications folder.If macOS still refuses, run this in Terminal and try again:
xattr -dr com.apple.quarantine /Applications/LumaBrowser.appVoice input (speech to text) is not available on macOS in this release; everything else, including local chat on Apple Silicon, is.
The AppImage needs a few system libraries that stock Ubuntu 24.04 (and most recent Debian-based distributions) do not ship. Install them first, then make the file executable:
sudo apt install libfuse2t64 libnspr4 libnss3 libasound2t64 libgomp1chmod +x LumaBrowser-1.8.1.AppImage && ./LumaBrowser-1.8.1.AppImageOn Ubuntu 22.04 and older the packages are named libfuse2 and libasound2. On Fedora use fuse-libs nspr nss alsa-lib libgomp. If the app still refuses to start, the error names the missing library; email us the line and we will add it here.
libgomp1 is needed by the chat engine, not the app, so its absence only shows up after Easy Setup has downloaded a model. Install it now and skip that surprise.
Chat uses the CUDA build automatically. Image generation on NVIDIA Linux currently uses the Vulkan build; see the image guide for what to expect.
Everything below is the same free app. These are just faster doors for people who live in a terminal. Full walkthrough on the agent quickstart.
npx lumabrowser startRequires Node 18+. Downloads the portable build for your OS on first run, caches it under ~/.lumabrowser/, and launches it. npm install -g lumabrowser works too.
docker run -d -p 3000:3000 -p 6080:6080 --shm-size=2g lumabyte/lumabrowser:latestHeadless container with the REST API on 3000 and a web desktop on 6080. Docker deployment guide.
Add {"command": "lumabrowser", "args": ["--mcp"]} under mcpServers in your host's config and restart it. Your agent gets navigate, click, fill, screenshot, and the rest. Setup and tool list.
REST API on http://localhost:3000, W3C WebDriver on 9515, Chrome DevTools Protocol on 9222. Selenium, Playwright, and Puppeteer scripts attach unchanged. API reference.
There is no feature held back for a paid plan, because there is no paid plan. This is the whole product.
LumaBrowser is free, with no paid tiers, account, or subscription. The local AI tools are included so you can explore what works on your hardware. Optional cloud providers charge separately if you choose to connect them.
If you are deploying LumaBrowser headless, in Docker, or across a fleet of machines and you need something we do not currently offer publicly, get in touch. We would genuinely like to hear what the requirement is.
Yes. Every feature is in the download above. There is no paid tier, no trial timer, no account, and no usage limit.
The installer is not code-signed yet, so Windows SmartScreen and some antivirus products warn about any new unsigned file. Click More info, then Run anyway. The size and SHA-512 checksum of every file are listed above so you can confirm you got the file we published.
The app is under 200 MB. The chat model is the big part: about 2 to 5 GB on a laptop, 6 to 20 GB on a gaming PC, 20 to 50 GB on a high-end machine. Easy Setup tells you the exact size before it downloads anything. Add about 6 GB if you turn on images.
Yes. Settings has a models folder setting; point it at another drive and the app moves or re-downloads there. Individual models can be deleted from the Setup tab. Uninstalling the app does not delete models unless you delete that folder.
No. Easy Setup downloads a local model sized to your hardware and everything runs on your own machine. If you would rather use OpenAI or Anthropic models, paste your own key and pay them directly. We never mark up tokens.
A version check-in (app version, platform, an installation identifier, and system metadata, so we can count active installs) and, if you use the Template Builder, generalized page templates with your inputs stripped. There is no third-party analytics or crash reporting in the app. Full details here.
See what's new in 1.8 for release notes, behaviour changes, and early-access features.