webdriver-bidi VS waggle-dance

fwiw, the Selenium project is now old enough to go to college (19 years this month!); it's not ready to retire just yet. (Side-note: Google Chrome is 15 years old. Age is just a number.) Selenium is still learning from other projects and implementing some new things. Specifically, check out the WebDriver BiDi project, adding a bidirectional protocol which was the core of what made Playwright and Puppeteer faster. Also, Selenium devs are working with the W3C to make this work for everyone.

https://github.com/w3c/webdriver-bidi

https://w3c.github.io/webdriver-bidi/

Is this new WebDriver BiDi available in any of these packages, and does it actually help with this?

If you want to learn more about WebDriver BiDi, you can read the WebDriver BiDi specification.

I guess I didn't understand what exactly you were talking about when talking about "this new standard": WebDriver BiDi or WebContainers.

WebDriver BiDi is on the standards track, that's true: https://w3c.github.io/webdriver-bidi/

One of the new features in the recently released Selenium 4 is support for new event-driven listeners which will be powered by the currently-in-draft BiDirectional (or BiDi) protocol (though the current Selenium implementation has some limitations, which we'll discuss later). In this article we'll discuss some of these new capabilities and demonstrate how to use them in Scala to inspect console logs and network requests made from the browser.

The new BiDirectional WebDriver Protocol is by far one of the most exciting recent developments in the Selenium project and it likely to deliver improvements in speed and stability that far outweigh expectations. As soon as it is available, it will become part of Nightwatch as well. You can follow the development on the Selenium website.

The explainer might be a better starting point: https://github.com/w3c/webdriver-bidi/blob/master/explainer....

There's also the webdriver-bidi spec being worked on by browser vendors that may provide a less hacky, more browser native CDP-style approach to this.

This seems very similar to LangSmith’s trace monitoring, which I have been leaning on heavily for observability. You also mention LlamaIndex— how do you see your project fitting into the ecosystem?

This is a great README, but I don’t think I would able to use this because it is serial.

In my experimental agent system, waggledance.ai, I have been working on a pre-agent step of [picking and synthesizing the right context and tools](https://github.com/agi-merge/waggle-dance/blob/main/packages...) for a given subtask of a larger goal, and it seems to be boosting results. It looks like now I have to try sub-question answering in the mix as well.

This is amazing. I will try to have it automate my system of agents web app (turtles all the way down) (shameless plug: https://github.com/agi-merge/waggle-dance)

- source code: https://github.com/agi-merge/waggle-dance

Any advice for trying to implement this in my project over at https://github.com/agi-merge/waggle-dance

Currently I am creating different agent types for planned subtasks using langchain, so perhaps implementing a custom AgentExecutor? Or would I need to lift it up higher in the logic stack? I am not sure that I understand how the graph search and thought-action-reflection selection process is deciding when and how to reflect if a branch fails, and how it backpropogates the failure to other nodes?

I have been working on a system of agents over at https://github.com/agi-merge/waggle-dance - I already split problems up into subtasks for agents to work on independently. I give agents access to vector databases, using a simple global key for now, but soon a context/parent/child key. Access to the vector DBs is proxied via tools (agents have to “call” saveMemory or retrieveMemory). I also check for looping/repetition FREQUENTLY using in-memory vector databases of the langchain agent callback events.

My opinion on this: eh, who cares? AutoGPT and similar are non-standard use cases for Vector DBs right now, and Vector DBs are useful for RAG.