<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Git on MacWorks</title><link>https://macworks.dev/tags/git/</link><description>Recent content in Git on MacWorks</description><generator>Hugo</generator><language>en</language><atom:link href="https://macworks.dev/tags/git/index.xml" rel="self" type="application/rss+xml"/><item><title>2026-05-16</title><link>https://macworks.dev/docs/week/simonwillison/simonwillison-2026-05-16/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://macworks.dev/docs/week/simonwillison/simonwillison-2026-05-16/</guid><description>&lt;h1 id="simon-willison--2026-05-16"&gt;Simon Willison — 2026-05-16&lt;a class="anchor" href="#simon-willison--2026-05-16"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;h2 id="highlight"&gt;Highlight&lt;a class="anchor" href="#highlight"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;p&gt;The standout update today is the release of &lt;code&gt;datasette-llm-limits 0.1a0&lt;/code&gt;, which introduces a practical way to manage LLM API costs directly within Datasette. It&amp;rsquo;s a highly useful piece of infrastructure for anyone building and exposing AI tools, solving the very real problem of managing usage limits for local or hosted LLM integrations.&lt;/p&gt;
&lt;h2 id="posts"&gt;Posts&lt;a class="anchor" href="#posts"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;p&gt;&lt;strong&gt;[datasette-llm-limits 0.1a0]&lt;/strong&gt;(&lt;a href="https://simonwillison.net/2026/May/15/datasette-llm-limits/#atom-everything"&gt;https://simonwillison.net/2026/May/15/datasette-llm-limits/#atom-everything&lt;/a&gt;)
Simon released an alpha version of &lt;code&gt;datasette-llm-limits&lt;/code&gt;, a new plugin that works alongside the &lt;code&gt;datasette-llm&lt;/code&gt; and &lt;code&gt;datasette-llm-accountant&lt;/code&gt; packages. It allows administrators to configure per-user or global spending limits for LLM usage inside of Datasette. This is a crucial addition for safely scaling AI-assisted database workflows by keeping API usage costs strictly under control.&lt;/p&gt;</description></item></channel></rss>