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

  1. Create an environment: conda create -n "omni" python==3.12 and conda activate omni.
  2. Install dependencies: pip install -r requirements.txt and download the weights as the README describes.
  3. 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

+85Oct 25 — Nov 22
25,54825,633

Author's description

A simple screen parsing tool towards pure vision based GUI agent

n8n-io

n8n

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.

211Kstars+2.3K in 28 dTypeScript

langgenius

dify

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.

162Kstars+2.2K in 30 dPython

langflow-ai

langflow

A visual builder for AI agents and workflows in Python: drag components, test the chain in chat and publish it as an API.

157Kstars+837 in 29 dPython

lobehub

lobehub

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.

86Kstars+2.5K in 29 dTypeScript

A large collection of ready-made n8n workflows with a searchable web UI. Find a similar automation and use it as a starting point.

57Kstars+220 in 29 dPython

huginn

huginn

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.

51Kstars+490 in 30 dRuby