@ms_aifrontiers: MagenticLite's models are now fully open source! MagenticBrain (14B orchestrator) and the Fara 1.5 computer-use family …
Summary
Microsoft AI Frontiers open-sources MagenticLite, including the MagenticBrain 14B orchestrator and Fara 1.5 computer-use models, now available on Hugging Face with open weights and the full application stack.
View Cached Full Text
Cached at: 07/24/26, 07:06 AM
MagenticLite’s models are now fully open source!
MagenticBrain (14B orchestrator) and the Fara 1.5 computer-use family (4B / 9B / 27B), previously on Microsoft Foundry, are now on Hugging Face with open weights.
The app, the harness, and every model in the stack are now openly available.
MagenticLite: http://aka.ms/magenticlite
Fara1.5: http://aka.ms/fara1.5-hf
MagenticBrain: http://aka.ms/magenticbrain-hf…
Fara1.5 blog: http://aka.ms/fara1.5
microsoft/magentic-ui
Source: https://github.com/microsoft/magentic-ui
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.
See it in action
Click any task below to expand and watch MagenticLite handle it end to end.
Fill expense forms
https://github.com/user-attachments/assets/a982b60d-127e-4310-96e6-9f094dffb7f0
Find prices for recipe ingredients
https://github.com/user-attachments/assets/7ff87917-752f-4e40-b319-8036e08ab8f9
Find and book a restaurant
https://github.com/user-attachments/assets/ee5f967e-ee1b-4554-b329-36b56b595aa4
Organize local files
https://github.com/user-attachments/assets/aff385dd-f856-4db4-8f26-08fd0f940aa4
Quick start
These steps get you running on macOS or Windows (WSL). Need more detail or a different platform? See the Installation Guide.
1. Install MagenticLite
# 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"
2. Run
magentic-ui --port 8081
Open 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.
Documentation
| 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 |
License
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.
Similar Articles
@ms_aifrontiers: Along with MagenticLite, we're introducing Fara1.5: a family of small browser agents at 4B, 9B, and 27B. It scores 63% …
Microsoft introduces the Fara1.5 family of small browser agents (4B, 9B, 27B) that achieve state-of-the-art performance on computer use benchmarks, scoring 63% on Online-Mind2Web and beating larger models like Operator and Gemini.
@MSFTResearch: New tools, models, repos, and papers out of Microsoft Research are here. Use AI and agents? It's worth watching: • Mage…
Microsoft Research announced new tools, models, repositories, and papers, including MagenticLite, agentic GitHub workflows, verification-first agents, and meaning-matching fine-tuning, during the Microsoft Research Forum virtual series.
@ms_aifrontiers: Fara1.5 is here! The tech report just landed on arXiv. New SOTA for computer use agents of its size, and it competes wi…
Fara1.5 is a family of native computer use agents trained using the FaraGen1.5 scalable data pipeline. The models achieve new state-of-the-art results on browser-use benchmarks, competing with much larger frontier models.
Mage (GitHub Repo)
Microsoft releases Mage, a family of lightweight 4B-parameter multimodal models for visual understanding and generation, including Mage-VL for image/video understanding and Mage-Flow for text-to-image generation and editing, designed for research and deployment on modest hardware.
@alvarobartt: GLM 5.2, open frontier-scale intelligence on Microsoft Foundry with AMD MI300X. Running a Codex goal with an open model…
GLM 5.2, an open frontier-scale AI model, is now available on Microsoft Foundry with AMD MI300X hardware, enabling efficient Codex goal execution.