Sharing a project I maintain. WebBrain puts an agent in the browser side panel: it can summarize/answer questions about the current page, extract tables and lists, fill forms, and navigate, using whichever model you configure (llama.cpp/Ollama/LM Studio locally, or any OpenAI-compatible API).
Some things that might interest people here:
- Plain vanilla JS, same codebase shipped for Chrome and Firefox
- Works with small local models: context trimming, a compact prompt mode, and a narrow tool set
- New MCP server, so Claude Code / Codex / OpenCode can use your real signed-in browser via the extension
Contributions welcome, especially site adapters and bug reports with a URL + the task that failed.
“Some things that might interest people here”
Clearly doesn’t get the audience. 😂
New account and only two posts, which advertises their slop-agent plugin that’ll probably log all your activity.
Yea, I think you’re about right.
you can do the opensource thing and fork it to remove the features you dont like.
also i have not looked at the src myself but its main purpose is use with local llms which can be reduced to mean: all your generated and collected data stays on your device.
You’re not wrong, at all. But I’d rather not use a plugin that:
I really don’t like the idea of running some random program/plugin/whatever in a session where it can access all of my data.
While Lemmy in general has a rather negative sentiment towards AI, that doesn’t mean there’s noone interested in such content. Especially when it comes to open source, open weights and full control (local/self hosting) AI can be a useful tool from my perspective where I see little reason to reject it just out of spite.
Even if you fundamentally oppose AI, I think it’s good to catch up with the news. I also read (and upvote) news about Trump, Musk, Putin etc. That doesn’t mean I agree or support their actions, just that I appeciate the information.
‘open source’ posts on social media these days appear to predominantly be ai crap
At some stage it is highly likely that will lead to significant government restrictions on open source because ‘unregulated ai’ cannot be trusted, and is always ‘escaping’ and ‘hacking’. The powers that be are already able to manipulate the general populace against open source, they don’t need our help.