An automation platform with a visual editor: connect services with blocks and add your own code or AI agents where needed. 400+ integrations, self-hostable.
All repositories
Automationmicrosoft
OmniParser
A model that parses a UI screenshot into buttons and fields so an agent can work from the screen alone, without access to page code.
Who it is for
People building vision-based GUI agents.
How to start
- Create an environment:
conda create -n "omni" python==3.12andconda activate omni. - Install dependencies:
pip install -r requirements.txtand download the weights as the README describes. - Run the demo:
python gradio_demo.py.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+151Sep 7 — Oct 7
Author's description
A simple screen parsing tool towards pure vision based GUI agent
More in «Automation»
A workspace for building AI apps: agentic workflows, RAG pipelines and a choice of models and tools in one interface. Deploy in the cloud or self-host.
A visual builder for AI agents and workflows in Python: drag components, test the chain in chat and publish it as an API.
A platform where you assemble a team of AI agents, schedule them and get reports. Works with many models; deploy on Vercel or with Docker.
A large collection of ready-made n8n workflows with a searchable web UI. Find a similar automation and use it as a starting point.
A long-running builder of "agents" that watch the web and events and act on your behalf: send emails, collect data, trigger chains. Runs on your own server.