Deployed 497e1a3 with MkDocs version: 1.6.1

index.html

@@ -74,7 +74,7 @@
     <div data-md-component="skip">
 
 
-        <a href="#overviews" class="md-skip">
+        <a href="#freeact" class="md-skip">
           Skip to content
         </a>
 
@@ -1000,7 +1000,8 @@
 
 
 
-<h1 id="overviews">Overviews</h1>
+<h1 id="freeact"><code>freeact</code></h1>
+<p>A lightweight Library for code-action based agents.</p>
 <h2 id="introduction">Introduction</h2>
 <p><code>freeact</code> is a minimalistic agent library that empowers language models to act as autonomous agents through executable <strong>code actions</strong>. By enabling agents to express their actions directly in code rather than through constrained formats like JSON, <code>freeact</code> provides a flexible and powerful approach to solving complex, open-ended problems that require dynamic solution paths.</p>
 <p>The library builds upon <a href="https://arxiv.org/abs/2402.01030">recent</a> <a href="https://arxiv.org/abs/2411.01747">research</a> demonstrating that code-based actions significantly outperform traditional agent approaches, with studies showing up to 20% higher success rates compared to conventional methods. While existing solutions often restrict agents to predefined tool sets, <code>freeact</code> removes these limitations by allowing agents to leverage the full power of the Python ecosystem, dynamically installing and utilizing any required libraries as needed.</p>

tutorials/index.html

@@ -880,7 +880,7 @@ <h1 id="overview">Overview</h1>
 <li><a href="skills/">Skill development</a> - Learn how to develop and improve custom skills in a conversation with the agent. The agent leverages its software engineering capabilities to support this process.</li>
 <li><a href="extend/">System extensions</a> - Learn how to define custom agent behavior and constraints through system extensions in natural language. This enables human-in-the-loop workflows, proactive agents, and more.</li>
 </ol>
-<p>All tutorials use a pre-built <a href="https://gradion-ai.github.io/ipybox/"><code>ipybox</code></a> <a href="../installation/#tutorial-docker-image">tutorial Docker image</a> for sandboxed code execution and the <code>freeact</code> <a href="#cli">CLI</a> for user-agent interactions. The <a href="basics/">Basic usage</a> tutorial additionally demonstrates the minimal Python code needed to implement a <code>freeact</code> agent.</p>
+<p>All tutorials use a pre-built <a href="https://gradion-ai.github.io/ipybox/"><code>ipybox</code></a> <a href="../installation/#tutorial-docker-image">tutorial Docker image</a> for sandboxed code execution and the <code>freeact</code> <a href="../cli/">CLI</a> for user-agent interactions. The <a href="basics/">Basic usage</a> tutorial additionally demonstrates the minimal Python code needed to implement a <code>freeact</code> agent.</p>