Computer-use agentsComputer vision

OmniParser

Breaks a screenshot down into buttons, fields and icons with labels so a regular language model can understand and control the screen. It does not click itself; it serves as the agent's eyes.

Developer
Microsoft, USA
First release
Oct 2024
Latest release
Feb 2025
Sizes
under 1B (detector + captioning)
License
Commercial use with conditionsIcon detector is AGPL-3.0, captioning model is MIT
Running
On your own serverAlso runs without a GPU
Industries
Software development, Documents and accounting
Deploy on your server Hugging Face GitHub

What it does

  • Mapping legacy software screens for automation
  • Preparing an agent to work in an interface
  • Checking that the required elements are on screen

Where it is used

IT and testingBack officeProcess automation (RPA)

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. OmniParser v2
  2. OmniParser v1

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can OmniParser be used in a commercial project?

With conditions. License: Icon detector is AGPL-3.0, captioning model is MIT. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does OmniParser need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does OmniParser support Russian?

Language does not matter for this model: it does not work with text.

Where can I download OmniParser and what does it cost?

The OmniParser weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Computer-use agentsUI-TARSByteDance Seed · ChinaCommercial use allowed

A model that looks at a screenshot and controls the mouse and keyboard itself: clicks, fills in fields, navigates menus. The first generation and 1.5-7B are open; UI-TARS-2 weights were not released.

DetailsImage + textFlorence-2Microsoft · USACommercial use allowed

A very small vision model: captions, object detection, segmentation and text reading from a single prompt. Runs even on a CPU.

DetailsComputer visionYOLO (Ultralytics)Ultralytics · USACommercial use with conditions

The most widely used real-time object detector: finds and marks items in video even on modest hardware. YOLOv5 came out back in 2020; the catalog starts from YOLOv8.

Details

Source: huggingface.co/microsoft/OmniParser-v2.0. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.