Magentic-UI + Fara-7B: A Local-First Computer-Use Agent You Can Actually Run

If you’ve been waiting for a computer-use agent you can run on your own machine (sandboxed, human-in-the-loop, open source), Microsoft’s Magentic-UI¹ is the repo to clone this week. It now leads with MagenticLite (“Big tasks. Small models.”), a redesign from Microsoft Research AI Frontiers that pairs a small-model orchestrator with a dedicated browser-use model and keeps you in control the whole way.

What it is

Magentic-UI is a research prototype for agentic web and computer tasks (form filling, price research, bookings, file organization) that you drive alongside the agent rather than handing it a blank cheque. MagenticLite splits the work across two models:

• MagenticBrain: the orchestrator, designed to run well on small models.
• Fara: a specialized browser-use model (Fara-7B) that actually drives the page.

Browser sessions run inside a lightweight VM sandbox called Quicksand, “so the agent can’t reach the rest of your machine without your say-so.” MIT-licensed, uv pip install "magentic_ui>=0.2.0", Python 3.12.

Why it’s worth exploring

• Local-first, bring-your-own-endpoint. It talks to any OpenAI-compatible endpoint, so you can run the whole loop against a model on your own hardware — no frontier API required.
• Human-in-the-loop by design. You co-plan the task, then co-task, stepping in to steer, approve, or take over at any point. It stops and checks in before critical actions instead of barreling ahead.
• Real isolation. The Quicksand sandbox contains the browser so a misbehaving agent (or a prompt-injected page) can’t touch your filesystem unprompted.
• Small-model economics. Capable agentic behaviour without frontier-scale compute or cost is the whole point of the redesign.
• A reference you can read. MIT license and a real UI make it a working blueprint if you’re building your own governed agent front-end.

Fara-7B, the interesting part

Fara-7B² is Microsoft’s first agentic small model built for computer use:

• 7B parameters, based on Qwen2.5-VL-7B, supervised fine-tuned on ~145K synthetic task trajectories generated through a Magentic-One multi-agent pipeline.
• Works like a human: it reads the screen and acts with mouse and keyboard across multi-step tasks, rather than calling bespoke tool APIs.
• Efficient. Microsoft reports it as the strongest small computer-use model it has benchmarked, competitive with much larger ones; independent write-ups clock it at ~16 steps per task on average versus ~41 for UI-TARS-1.5-7B.
• Runs where you want. MIT-licensed on Hugging Face³ and Microsoft Foundry, with quantised GGUF builds for LM Studio and Ollama, a fara-cli, and vLLM serving on a single 24 GB GPU.

The local-first setup, concretely

Point Magentic-UI’s model config at a local OpenAI-compatible endpoint (e.g. http://localhost:5000/v1) served by vLLM, Ollama, or LM Studio running Fara-7B. The browser pane, the model, and your data all stay on your machine; the agent loop costs you GPU time, not per-token cloud spend. For anyone in a regulated shop who can’t send screens and page contents to a hosted API, that’s the difference between “interesting demo” and “something I can actually pilot.”

Bottom line

References

1. Microsoft’s Magentic-UI — github.com ↩ ↩²

2. Fara-7B — github.com ↩

3. Hugging Face — huggingface.co ↩