HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
datasette
datasette-agent
Python2026–2026
datasette / datasette-agent

datasette-agent

An LLM-powered agent for Datasette

5Distinct people
6Mentions
0Explicit recommenders
121GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

An LLM-powered agent for Datasette

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by day6 dated mentions

Observed mentions: 2026-05-21 20:15:11 UTC to 2026-06-12 11:27:05 UTC.

0123452026-05-21 00:00:00 UTC to 2026-05-22 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsMay 212026-05-22 00:00:00 UTC to 2026-05-23 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-23 00:00:00 UTC to 2026-05-24 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-24 00:00:00 UTC to 2026-05-25 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-25 00:00:00 UTC to 2026-05-26 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-26 00:00:00 UTC to 2026-05-27 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-27 00:00:00 UTC to 2026-05-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-28 00:00:00 UTC to 2026-05-29 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-29 00:00:00 UTC to 2026-05-30 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-30 00:00:00 UTC to 2026-05-31 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-05-31 00:00:00 UTC to 2026-06-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-01 00:00:00 UTC to 2026-06-02 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsJun 12026-06-02 00:00:00 UTC to 2026-06-03 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-03 00:00:00 UTC to 2026-06-04 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-04 00:00:00 UTC to 2026-06-05 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-05 00:00:00 UTC to 2026-06-06 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-06 00:00:00 UTC to 2026-06-07 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-07 00:00:00 UTC to 2026-06-08 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-08 00:00:00 UTC to 2026-06-09 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-09 00:00:00 UTC to 2026-06-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-10 00:00:00 UTC to 2026-06-11 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-11 00:00:00 UTC to 2026-06-12 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-06-12 00:00:00 UTC to 2026-06-13 00:00:00 UTC (exclusive): 5 mentions; 0 submissions, 5 commentsJun 12

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
May 212026-05-21 00:00:00 UTC2026-05-22 00:00:00 UTC101
May 222026-05-22 00:00:00 UTC2026-05-23 00:00:00 UTC000
May 232026-05-23 00:00:00 UTC2026-05-24 00:00:00 UTC000
May 242026-05-24 00:00:00 UTC2026-05-25 00:00:00 UTC000
May 252026-05-25 00:00:00 UTC2026-05-26 00:00:00 UTC000
May 262026-05-26 00:00:00 UTC2026-05-27 00:00:00 UTC000
May 272026-05-27 00:00:00 UTC2026-05-28 00:00:00 UTC000
May 282026-05-28 00:00:00 UTC2026-05-29 00:00:00 UTC000
May 292026-05-29 00:00:00 UTC2026-05-30 00:00:00 UTC000
May 302026-05-30 00:00:00 UTC2026-05-31 00:00:00 UTC000
May 312026-05-31 00:00:00 UTC2026-06-01 00:00:00 UTC000
Jun 12026-06-01 00:00:00 UTC2026-06-02 00:00:00 UTC000
Jun 22026-06-02 00:00:00 UTC2026-06-03 00:00:00 UTC000
Jun 32026-06-03 00:00:00 UTC2026-06-04 00:00:00 UTC000
Jun 42026-06-04 00:00:00 UTC2026-06-05 00:00:00 UTC000
Jun 52026-06-05 00:00:00 UTC2026-06-06 00:00:00 UTC000
Jun 62026-06-06 00:00:00 UTC2026-06-07 00:00:00 UTC000
Jun 72026-06-07 00:00:00 UTC2026-06-08 00:00:00 UTC000
Jun 82026-06-08 00:00:00 UTC2026-06-09 00:00:00 UTC000
Jun 92026-06-09 00:00:00 UTC2026-06-10 00:00:00 UTC000
Jun 102026-06-10 00:00:00 UTC2026-06-11 00:00:00 UTC000
Jun 112026-06-11 00:00:00 UTC2026-06-12 00:00:00 UTC000
Jun 122026-06-12 00:00:00 UTC2026-06-13 00:00:00 UTC505

What Hacker News says

6 sources
They might also ask why a bunch of static CSS inside a bunch of JavaScript is hiding inside __init__.py[0] - hopefully before trying to fix some detail of the CSS. (I'm surprised to see it actually, since my own use of Claude has mostly yielded well-structured code. But I'm not doing proper vibe-coding, more like friendly Socratic arguing with another engineer who happens to be a robot.) [0] https://github.com/datasette/datasette-agent/blob/main/datas...
In Claude Fable is relentlessly proactive
This to me reads like a poignant commentary on the catastrophic loss of human agency, with the actual commit being highly revealing [0]. Author wants to hide a horizontal scrollbar. Any junior frontend dev worth their salt will be asking right away "where do I stick `overflow-x: hidden;`?" A complete solution will then require hitting "Inspect element" in the browser to find the CSS class and running (rip)grep to find where it is in code, to then add a single line to. An actual proactive programmer might start asking more pointed questions like what content does an empty textbox have that it overflows? And why do I need to insert this workaround that treats the symptom and not the root cause in two different places? Isn't it better to style `textarea` once? Etc, etc. [0] https://github.com/datasette/datasette-agent/commit/a75a8b72...
In Claude Fable is relentlessly proactive
30 seconds or a minute? Look at the diff he links to: https://github.com/datasette/datasette-agent/commit/a75a8b72... Every browser has an inspector that can show you which element is causing overflow. You walk through the tree, find the offender, and add min-width or overflow. Zero tokens, just like in the old days! Now, granted, because the garbage LLM code he’s working with has CSS inside HTML inside JavaScript inside Python (I wish I were kidding), finding the styles in his codebase might’ve taken a minute. But even then!
In Claude Fable is relentlessly proactive

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.