Big tasks. Small models.
MagenticLite is the next generation of Magentic-UI — an agentic application from Microsoft AI Frontiers, redesigned to do more with less. It pairs an on-device-friendly orchestrator model (MagenticBrain) with a specialized browser-use model (Fara) so you can automate real work without depending on frontier-scale compute.
- Built for small models, efficient by design. Strong agentic performance without heavy compute — no frontier-scale models required.
- Works across the browser and your local file system. Web research, form filling, file management — in one workflow.
- Keeps you in the loop and in control. Steer, approve, or take over at any point. MagenticLite stops and checks in before taking critical actions.
- Safe by design. Browser sessions run inside a lightweight VM sandbox (Quicksand) so the agent can't reach the rest of your machine without your say-so.
Click any task below to expand and watch MagenticLite handle it end to end.
Fill expense forms
MagenticLite.-.Fill.Expenses.Forms.-.Final.Demo.mp4
Find prices for recipe ingredients
MagenticLite.-.Find.Prices.for.Recipe.Ingredients.-.Final.Demo.mp4
Find and book a restaurant
MagenticLite.-.Finding.and.Booking.a.Restaurant.-.Final.Demo.mp4
Organize local files
MagenticLite.-.Organize.Local.Files.-.Final.Demo.mp4
These steps get you running on macOS or Windows (WSL). Need more detail or a different platform? See the Installation Guide.
# Create a project directory
mkdir magentic-lite && cd magentic-lite
# Create and activate a virtual environment
uv venv --python=3.12 --seed .venv
source .venv/bin/activate
# Install the latest 0.2.x release from PyPI
uv pip install "magentic_ui>=0.2.0"magentic-ui --port 8081Open http://127.0.0.1:8081/ and follow the in-app onboarding to connect a model endpoint. If you don't have one yet, see the Model Hosting Guide.
Looking for the previous Magentic-UI 0.1 release (optimized to run with frontier models)? It lives on the
magentic-ui-0.1branch.
| Doc | What's in it |
|---|---|
| Installation | Supported platforms, macOS / WSL prerequisites, install + run commands |
| Build from source | How to run MagenticLite from a clone of this repo (uv sync, pnpm dev, etc.) |
| Model hosting guide | End-to-end walkthrough of standing up a model endpoint and connecting MagenticLite to it |
| Configuration | Sandbox, agent mode, tool approval, full config.yaml example |
| Troubleshooting | Common errors and how to fix them |
| Limitations | Tasks and usage patterns MagenticLite doesn't handle well today |
| Transparency Note | Intended uses, responsible-use guidance, risks, and mitigations |
Microsoft, and any contributors, grant you a license to any code in the repository under the MIT License. See the LICENSE file.
Microsoft, Windows, Microsoft Azure, and/or other Microsoft products and services referenced in the documentation may be either trademarks or registered trademarks of Microsoft in the United States and/or other countries. The licenses for this project do not grant you rights to use any Microsoft names, logos, or trademarks. Microsoft's general trademark guidelines can be found at http://go.microsoft.com/fwlink/?LinkID=254653.
Any use of third-party trademarks or logos are subject to those third-party's policies.
Privacy information can be found at https://go.microsoft.com/fwlink/?LinkId=521839.
Microsoft and any contributors reserve all other rights, whether under their respective copyrights, patents, or trademarks, whether by implication, estoppel, or otherwise.