LaVague Weekly Update #5
LaVague: A Large Action Model framework for building Web Agents

LaVague Weekly Update #5

Welcome to our weekly updates, where we announce the latest news on our open-source framework for Web Agents & share what's coming next and how you can get involved!

Laura Yie

Welcome to our fifth weekly dev update.

Here's what we got up to last week:

  • 📊 The Evaluator module was launched for easy benchmarking of LLMs and retrievers. Find out how to use it do your own benchmarks here.
  • 🌊 We held a webinar on the Navigation Engine which you can watch here.
  • 📑 We continued to add content to our docs.

🏆 Community Pull Requests merged:

  • A LocalLogger module was added which allows you to log to a local file.
  • Methods to return the nodes retrieved during the last agentic run were added to the Agent module.
  • Caching for API calls was added.

For more issues you can contribute to, you can see the full list of our help wanted GitHub issues here - but below, you can see a few of the tasks we'd love your help on.

📢 Help wanted:

Coming soon:

  • 🌐 A LaVague browser extension.
  • 🔒 Safeguards to avoid arbitrary code execution and ensure only certain actions can be executed.
  • 🐞 An end-to-end debugging guide in the docs.
  • 🌴 Exploration of leveraging.

Thanks for continuing to follow our journey!