Show HN: Gauge – Open-Source CLI to recursively improve your docs
0 comments
- Points43
- Comments10
0 comments
Hi HN, I’m Evan from Gauge. We’re open-sourcing our CLI to recursively improve your docs for coding agents. The CLI includes a local execution backend, so you don't need an account to try it. Explainer video here: https://youtu.be/zhLUlIKB1Mg The CLI supports a hillclimbing loop: - set up tasks for coding agents that would need your docs, like 'set up Gauge CI checks' - run the tasks - analyze session transcripts for friction or failures - create variants of your docs to resolve the issues -…
Story details from Hacker News ↗ · linked article on github.com.
Show HN: Gauge – Open-Source CLI to recursively improve your docs was first seen on Hacker News · Front page on Nov 4, 2026. Since then it has appeared in 113 checks on 5 different days, across 3 lists (Hacker News · Front page, Hacker News · Show HN, Hacker News · Show HN · this week). Its best position was #28 of 30, reached on Nov 5, 01:07 UTC. It dropped off the list after Nov 8, 14:50 UTC.
Position on Hacker News · Front page at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hacker News.
| List | Best | Days | Checks | Last seen |
|---|---|---|---|---|
| Hacker News · Front page | #28 | 2 | 20 | |
| Hacker News · Show HN | #1 | 1 | 37 | |
| Hacker News · Show HN · this week | #25 | 3 | 56 |
A few top-level comments from Hacker News, shortened. Read the full thread on Hacker News.
I have been doing this process by hand. Try to do something. Observe friction. Document how to avoid it. Rinse and repeat. It works and raises the quality going forward. Most importantly, the vast majority of my tokens are spent moving my project forward. I would be extremely leery to use an automated hill-climbing…
This is definitely something the companies most focused on agent experience are thinking about: - https://supabase.com/evals - https://nextjs.org/evals What is a better analogy for how you think developer tools should think about agent experience: an RL environment (hillclimbing a task like you mention), or a test…
Your idea of using a hillclimbing loop for improving documents is interesting. It looks like you found problems by looking at conversation records. Can you explain the measurements you use to know if a version of a document solves a problem? Also what do you do when different coding assistants give comments, about…
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 8, 14:50 UTC, after 5 days of trending.
#28 on Hacker News · Front page, on Nov 5, 01:07 UTC. Trendoday checks this list every 15 minutes.
It was first seen on Nov 4, 2026 and has been on the list on 5 days (113 checks) since.
43 points and 10 comments; submitted by 0x63_Problems on Nov 4, 2026.