#865 · Primary category: AI Agents & Automation

LaVague

ai browser large-action-model llm oss rag

Large Action Model framework to develop AI Web Agents

Project last updated:01/21/25

GitHub Stars

6.4K

Forks

573

Contributors

31

License

Apache-2.0

Why we included this project

LaVague is an open-source framework for building AI web agents that act on plain-language objectives. Hand it a task like 'print the installation steps for Hugging Face's Diffusers library' and it manages the whole flow: a World Model reads the current page and decides what needs to happen, then an Action Engine compiles those instructions into Selenium or Playwright code and executes them. The appeal is that you don't build any of this yourself. You wire objectives into your product and the framework plans and performs the browser steps. There's also companion tooling for QA engineers: LaVague QA turns Gherkin specs into automated web tests using the same underlying machinery. If you want LLM-driven browser automation without assembling the pieces by hand, this is a solid starting point.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category