talk2dom is a focused utility that solves one of the hardest problems in browser automation and UI testing:
✅ Finding the correct UI element on a page.
If you like talk2dom, consider giving it a star on GitHub! It helps others discover the project and keeps the community growing.
In most automated testing or LLM-driven web navigation tasks, the real challenge is not how to click or type — it's how to locate the right element.
Think about it:
- Clicking a button is easy — if you know its selector.
- Typing into a field is trivial — if you've already located the right input.
- But finding the correct element among hundreds of
<div>,<span>, or deeply nested Shadow DOM trees? That's the hard part.
talk2dom is built to solve exactly that.
Our goal is not to control the browser — you still control your browser. Our goal is to find the right DOM element, so you can tell the browser what to do.
- 🔁 Persistent session for multi-step interactions
- 🧠 LLM-powered understanding of high-level intent
- 🧩 Outputs: actionable XPath/CSS selectors or ready-to-run browser steps
talk2dom powers a production-ready hosted service — making it easy to integrate into your automation agents, testing pipelines, and internal tools.
Join our community on Discord to get support, share ideas, and connect with other users:
👉 Join Talk2Dom Discord
# Clone the repository
git clone https://github.com/itbanque/talk2dom.git
cd talk2dom
# Launch the talk2dom-integrated stack
docker compose upThe API is available at http://localhost:8000/docs with full OpenAPI schema and interactive Swagger UI.
The hosted version of talk2dom includes a full-featured backend system with:
- 🔐 User Authentication & Account Management — including registration, login, and session handling
- 🧾 Project Management — organize different workflows under separate projects
- 🔑 API Key Management — issue and revoke keys per project
- 💳 Subscription & Credit System — users can purchase or subscribe for API usage credits (Stripe supported)
- 🧠 Intelligent Selector Caching — automatic deduplication and re-use of prior LLM results via PostgreSQL
This transforms talk2dom from a Python utility into a scalable service with all necessary infrastructure to support production-grade applications.
Deploy on your own cloud or integrate with tools like Zapier, Retool, or internal RPA systems.
For detailed deployment instructions, contact us via GitHub discussions.
This project is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License.
You may:
- ✅ Use, modify, and share the code for personal or research purposes
- ❌ Not use it in commercial applications without permission
- ✅ You must give appropriate credit, provide a link to the license, and indicate if changes were made.
📩 For commercial licensing, please contact: contact@itbanque.com
Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.
We’d love to hear how you're using talk2dom in your AI agents or testing flows.
Feel free to open issues or discussions!
You can also tag us on GitHub if you’re building something interesting with talk2dom!
⭐️ If you find this project useful, please consider giving it a star!