What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- How does caching work and whether switching models destroys cached input savings.From this comment
- Whether the project began in Python and was later rewritten in Rust.From this comment
- How it compares with an existing similar gateway tool and what differentiates it.From this comment
- What online signal recalibrates simulated rankings against real task success and whether semantic caching is planned.From this comment
- What the business model is and how the company earns money.From this comment
What they doubted or pushed back on our summary
- Swapping among many models may raise costs sharply despite performance gains.From this comment
- The caching concern should be settled before anyone starts swapping models.From this comment
- Calling it an open version of a specific brand name in the title is misleading.From this comment
- Several other routers directly compete, so the difference from them needs explaining.From this comment
What the maker answered our summary
12 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- Routing usually concludes that one model already fits the task, so switching happens rarely.From this comment
- The project was indeed first written in Python and later moved to Rust.From this comment
- Switching generally happens at task boundaries rather than continuously between models.From this comment
- Effort levels are also chosen, and a hosted marketplace is offered alongside bring-your-own-key.From this comment
What a builder can take from it: Builders should address caching costs and clear differentiation before launching a router, since those dominate reader concern. our reading
The title, taken apart our calculation
This post got 222 points; the median for all 1442 posts is 112. In Open source projects (328 posts) the median is 103 points and 38 comments.
When it was posted our calculation
Thursday at 21:00 UTC. Of 1,956 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 55 (2.8%) reached 50 points; on Thursdays it was 2.7% of 8,077. The average over all hours is 2.9%. One post's time does not explain its result; the full table of hours is on the Show HN hub.
Check your title our calculation
Type the title you plan to post. It is compared with 1,442 Show HN posts that reached 50 or more points: its length, its shape, and how posts of that length and shape did. Nothing is sent anywhere.
Type a title above to see where it sits.
Draft my Show HN post
Paste your site address and get title options and a first comment for your own Show HN post, written from what your site says and checked against the numbers above. Nothing is posted for you.
Free to try and no account needed. FoxPlug is for people who ship several projects and keep stalling on telling anyone: it turns what you ship into posts you approve before anything goes out. See what each plan includes.
More Open source projects teardowns
Points, comments, titles and times are Hacker News's own numbers, read from the post itself, last updated Nov 2026. Summaries of what people said are ours, written in our own words, and each one links to the comment it came from. Percentages and medians marked "our calculation" are computed from the posts counted on the page: they describe what happened, not what will happen to your post. FoxPlug posts nothing for you. Plans and limits are on the pricing page. Questions: support.
After the launch post: a changelog your users read
A launch brings visitors once. FoxPlug turns what you ship afterwards into a public changelog and ready posts, so the next visitor finds something new.
Start your changelog See a SaaS changelog example
Free to start. Pro is a month.
FoxPlug Pro
- A public changelog page and feed for each project
- Visual cards and walkthrough videos made from what you shipped
- Posts for X, LinkedIn and dev.to written from your changes
- Connect GitHub and the tools you build with