Re:Show HN: PageAgent, A GUI agent that lives inside your we...
by darkvertex on Thursday March 05, 2026 @11:53PM
(#47271030)
Or why not stay fully local with WebLLM...
https://webllm.mlc.ai
Re:Show HN: PageAgent, A GUI agent that lives inside your we...
by simon_luv_pho on Friday March 06, 2026 @12:44AM
(#47271328)
That looks great! I also thought about calling the Gemini nano model embedded into Chrome (only extensions can do that). But after some testing on smaller models I found that anything smaller than 9b can’t really handle the complex tool call schema I use.
Qwen3.5 4b is quite good but still gives messy json quite often. But it’s very promising!
Maybe after one more model iteration or some fine-toning we can go fully embedded?
The free testing LLM is Qwen hosted by Aliyun. Qwen and DeepSeek are the only ones I can afford to offer for free. It's just there to lower the try-out barrier; please DO NOT rely on it.
The library itself does NOT include any backend service. Your data only goes to the LLM api you configured.
I tested it on local Ollama models it works fine.