Autonode: Automate web interactions and extract data

Understand the project

Practical overview

Use Autonode when a web task can be described as page elements and actions and you want to configure a visual, graph-guided automation system.

Developers exploring visual GUI automation for web workflows.
Teams seeking to automate defined page interactions or extract information through a mapped navigation flow.

Before you choose

The repository documents a local setup using Python and Docker Compose, with a service health URL and API documentation URL.

Automation planning depends on preparing a JSON site graph for the target navigation and actions.
The README describes creating a planner prompt using the template in openai_prompts.py.
The documented setup uses Docker Compose and separate environment files for the autonode, yolo and ocr modules.
The README gives a local Swagger documentation address at http://localhost:8001/docs.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Start the documented Docker Compose service and check its health endpoint.

Clone the AutoNode repository and change into its root directory.
Copy .env.example to .env for each of the autonode, yolo and ocr modules.
Run docker compose -f docker-compose.yaml up --build in the repository directory.
Open http://localhost:8001/health in a browser to check whether the server is running.

The service is started through Docker Compose, and its documented health URL can be opened to check server status.

The guide covers setup and a health check, not execution of a specific automation or extraction task.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 17 October 2026
Original website title: TransformerOptimus/AutoNode · Official homepage title · retained in its source language