<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Open Source on Multivergence.com</title>
    <link>https://multivergence.com/tags/open-source/</link>
    <description>Recent content in Open Source on Multivergence.com</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sun, 18 Oct 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://multivergence.com/tags/open-source/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Multivergence Launches as Open Source Forkable State for AI Agents</title>
      <link>https://multivergence.com/multivergence-launches-as-open-source-forkable-state-for-ai-agents/</link>
      <pubDate>Sun, 18 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://multivergence.com/multivergence-launches-as-open-source-forkable-state-for-ai-agents/</guid>
      <description>&lt;p&gt;Multivergence 0.1 is out, open source under the Apache License 2.0. It&amp;rsquo;s a state engine for software that keeps several possible futures open at once: fork the state into branches, give each a weight, constraints and a deadline, let evidence thin them out, and promote the one that&amp;rsquo;s left. The code is on &lt;a href=&#34;https://github.com/multivergence/multivergence&#34;&gt;GitHub&lt;/a&gt;, and ready-built binaries for Linux, macOS and Windows are on the &lt;a href=&#34;https://multivergence.com/download/&#34;&gt;download page&lt;/a&gt;.&lt;/p&gt;&#xA;&lt;p&gt;The first users in mind are AI agents that try before they commit. They fork a plan per approach, feed tool results back as facts and likelihoods, and promote the plan that survives. The &lt;a href=&#34;https://multivergence.com/forkable-state-gives-ai-agents-a-real-way-to-try-before-they-commit/&#34;&gt;explainer&lt;/a&gt; goes through why that job belongs in the state, where every agent can share it.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
