Live data from Hacker News

Show HN: Bring-your-own-key browser extension for summarizing HN posts with LLMs

github.com

1–10 of 33 posts

Show HN: Bring-your-own-key browser extension for summarizing HN posts with LLMs

#1
Hi Hacker News,

I developed an open source browser extension for summarizing Hacker News articles with OpenAI and Anthropic LLMs. It currently supports Chrome [1] and Firefox [2] (desktop).

The extension adds the summarize buttons to the HN front page and article pages.

It is bring-your-own-key, i.e. there's no back end behind it and the usage is free, you insert your API key and pay only for tokens to your LLM provider.

[1] https://chromewebstore.google.com/detail/hacker-news-tldr/oo...

[2] https://addons.mozilla.org/ru/firefox/addon/hacker-news-tl-d...

Show HN: Bring-your-own-key browser extension for summarizing HN posts with LLMs
github.com

Re: Show HN: Bring-your-own-key browser extension for summarizing HN posts with LLMs

#7
post #3

Would be nice to be able to provide your own endpoint so it could be directed to a local llm.

Thanks, good idea, this should be possible.

That would be a pretty killer feature IMHO. Ollama's API is pretty straightforward: https://github.com/ollama/ollama/blob/main/docs/api.md

There is also (or at least used to be?) an OpenAI compatible API layer for Ollama so that may be an option as well, though my understanding is there are some downsides to using that.

Note: This comment and the link are just meant as references/conveniences, not intended as a request for free labor. Thanks for opening up the code!

Re: Show HN: Bring-your-own-key browser extension for summarizing HN posts with LLMs

#9
post #6

This sounds possibly useful, but I just don't trust extensions unless I can see the code.

https://github.com/ivanyu/hn-tldr-extension

I am an idiot for not looking at OP link. jeez. thanks.

Re: Show HN: Bring-your-own-key browser extension for summarizing HN posts with LLMs

#10
post #3

Earlier quoted context omitted.

Thanks, good idea, this should be possible.

That would be a pretty killer feature IMHO. Ollama's API is pretty straightforward: https://github.com/ollama/ollama/blob/main/docs/api.md There is also (or at least used to be?) an OpenAI compatible API layer for Ollama so that may be an option as well, though my understanding is there are some downsides to using that. Note: This comment and the link are just meant as references/conveniences, not intended as a reque…

Forget ollama, just changing the URL from openai to your local server is enough, llama.cpp has a compatible endpoint. Most people just don't bother giving the option since you get a CORS error if it doesn't have a valid cert.
Post reply on HN