←back to thread

Show HN: A web browser agent in your Chrome side panel

(github.com)
127 points parsabg | 3 comments | 18 May 25 11:48 UTC | HN request time: 0.672s | source

Hey HN,

I'm excited to share BrowserBee, a privacy-first AI assistant in your browser that allows you to run and automate tasks using your LLM of choice (currently supports Anthropic, OpenAI, Gemini, and Ollama). Short demo here: https://github.com/user-attachments/assets/209c7042-6d54-4fc...

Inspired by projects like Browser Use and Playwright MCP, its main advantage is the browser extension form factor which makes it more convenient for day to day use, especially for less technical users. Its also a bit less cumbersome to use on websites that require you to be logged in, as it attaches to the same browser instance you use (on privacy: the only data that leaves your browser is the communication with the LLM - there is no tracking or data collection of any sort).

Some of its core features are as follows:

- a memory feature which allows users to memorize common and useful pathways, making the next repetition of those tasks faster and cheaper

- real-time token counting and cost tracking (inspired by Cline)

- an approval flow for critical tasks such as posting content or making payments (also inspired by Cline)

- tab management allowing the agent to execute tasks across multiple tabs

- a range of browser tools for navigation, tab management, interactions, etc, which are broadly in line with Playwright MCP

I'm actively developing BrowserBee and would love to hear any thoughts, comments, or feedback.

Feel free to reach out via email: parsa.ghaffari [at] gmail [dot] com

-Parsa

1. nico ◴[18 May 25 13:35 UTC] No.44021331[source]▶
Looks amazing, love it. And I see that in your roadmap the top thing is saving/replaying sessions

Related to that, I'd suggest also adding the ability to "templify" sessions, ie. turn sessions into sort of like email templates, with placeholder tags or something of the like, that either ask the user for input, or can be fed input from somewhere else (like an "email merge")

So for example, if I need to get certain data from 10 different websites, either have the macro/session ask me 10 times for a new website (or until I stop it), or allow me to just feed it a list

Anyway, great work! Oh also, if you want to be truly privacy-first you could add support for local LLMs via ollama

replies(1): >>44021734 #
2. parsabg ◴[18 May 25 14:38 UTC] No.44021734[source]▶
Thank you!

I like that suggestion. Saved prompts seem like an obvious addition, and having templating within them makes sense. I wonder how well would "for each of the following websites do X" prompts work (so have the LLM do the enumeration rather than the client - my intuition is that it won't be as robust because of the long accumulated context)

Edit: forgot to mention it does support Ollama already

replies(1): >>44022294 #
3. nico ◴[18 May 25 16:00 UTC] No.44022294[source]▶
Yeah, that "for each" needs to be code instead of prompt. Ideally you want to only use the LLM for the first time you run the task, but after "figuring out the path", you want to run that directly through code

So for the example above, the user might have to do: "do this for this website", then save macro, then create template, then run template with input: [list of 10 websites]