<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Releases on tokening.net</title>
    <link>https://tokening.net/tags/releases/</link>
    <description>Recent content in Releases on tokening.net</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 26 Oct 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://tokening.net/tags/releases/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Tokening 0.1 Gives AI Agents Single-Use API Grants</title>
      <link>https://tokening.net/tokening-0.1-gives-ai-agents-single-use-api-grants/</link>
      <pubDate>Mon, 26 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://tokening.net/tokening-0.1-gives-ai-agents-single-use-api-grants/</guid>
      <description>&lt;p&gt;An agent needs to fix the title of one blog post. To do that today it usually gets an account password, and that password can also delete the post, publish drafts and change the site&amp;rsquo;s settings. It works tomorrow too, and next month. Tokening is a small gateway that hands the agent something much narrower: a grant for this post, these fields, one use and a fifteen-minute deadline.&lt;/p&gt;&#xA;&lt;p&gt;The agent sends its calls to Tokening with the grant&amp;rsquo;s secret. Tokening checks each call against the grant. If it fits, Tokening spends the use, adds the real credential from its encrypted vault and passes the call on. If it doesn&amp;rsquo;t fit, the call stops there and the agent gets a reason in plain words: &amp;ldquo;Grant is bound to id 2; call sent id 3.&amp;rdquo;&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
