fara
Fara-7B: An Efficient Agentic Model for Computer Use
Running a compact open-weight computer-use model locally, where a seven-billion-parameter agent is preferred to a larger hosted one.
You need the strongest available computer-use performance; the project positions it as state of the art within its size class rather than overall.
About fara
Fara-7B is Microsoft's first agentic small language model (SLM) designed specifically for computer use. With only 7 billion parameters, Fara-7B is an ultra-compact Computer Use Agent (CUA) that achieves state-of-the-art performance within its size class and is competitive with larger, more resource-intensive agentic systems.
Try Fara-7B locally as follows (see Installation for detailed instructions on Windows ) or via Magentic-UI:
To try Fara-7B inside Magentic-UI, please follow the instructions here Magentic-UI + Fara-7B. You will need to serve the model as before, but instead of fara-cli you can use Magentic-UI which has a nice UI (see video demos below).
fara is listed in this index written primarily in Python, with 6.3k stars on GitHub. Its latest recorded repository push was in September 2026; that is not an ASE editorial review date.
pip install -e .