Merge branch 'main' into hiro/kiosk_mode

Author: hiroTamada

browsers/extensions.mdx

@@ -88,7 +88,7 @@ kernel extensions upload ./downloaded-extension --name my-extension
 
 ## Loading an extension into a running browser
 
-If you have a browser running and would like to load an extension into it after the browser session has started, Kernel also allows you to do that via the CLI (or [API](http://localhost:3000/api-reference/browsers/ad-hoc-upload-one-or-more-unpacked-extensions-to-a-running-browser-instance)):
+If you have a browser running and would like to load an extension into it after the browser session has started, Kernel also allows you to do that via the CLI (or [API](/api-reference/browsers/ad-hoc-upload-one-or-more-unpacked-extensions-to-a-running-browser-instance)):
 
 ```bash CLI
 kernel browsers extensions upload <session_id> ./my-extension

docs.json

@@ -99,11 +99,13 @@
           {
             "group": "Integrations",
             "pages": [
+              "integrations/overview",
               "integrations/browser-use",
               {
                 "group": "Computer Use",
                 "pages": [
                   "integrations/computer-use/anthropic",
+                  "integrations/computer-use/gemini",
                   "integrations/computer-use/openai"
                 ]
               },

integrations/computer-use/gemini.mdx

@@ -0,0 +1,31 @@
+---
+title: "Gemini"
+---
+
+Google's [Gemini 2.5 Computer Use model](https://blog.google/technology/google-deepmind/gemini-computer-use-model/) is a specialized model built on Gemini 2.5 Pro's capabilities to power agents that can interact with user interfaces.
+
+By integrating Gemini 2.5 Computer Use with Kernel, you can run these AI-powered browser automations on cloud-hosted infrastructure, eliminating the need for local browser management and enabling scalable, reliable AI agents.
+
+## Quick setup with our example template
+
+Get started quickly with our TypeScript template that demonstrates Gemini 2.5 Computer Use with Kernel.
+
+Check out the [Open-source Gemini Template](https://github.com/onkernel/ts-stagehand-google-cua-agent) repository for a complete working example that shows how to:
+- Set up Gemini 2.5 Computer Use with Kernel
+- Use Stagehand for browser automation
+- Run AI-powered web interactions on cloud infrastructure
+
+## Benefits of using Kernel with Gemini Computer Use
+
+- **No local browser management**: Run Computer Use automations without installing or maintaining browsers locally
+- **Scalability**: Launch multiple browser sessions in parallel for concurrent automations
+- **Stealth mode**: Built-in anti-detection features for web interactions
+- **Session persistence**: Maintain browser state across automation runs
+- **Live view**: Debug your automations with real-time browser viewing
+
+## Next steps
+
+- Check out [live view](/browsers/live-view) for debugging your automations
+- Learn about [stealth mode](/browsers/stealth) for avoiding detection
+- Learn how to properly [terminate browser sessions](/browsers/termination)
+- Learn how to [deploy](/apps/deploy) your Computer Use app to Kernel

integrations/magnitude.mdx

@@ -27,7 +27,12 @@ const client = new Kernel({
     apiKey: process.env.KERNEL_API_KEY,
 });
 
-const kernelBrowser = await client.browsers.create();
+const kernelBrowser = await client.browsers.create({
+    viewport: {
+        width: 1920,
+        height: 1080
+    }
+});
 
 console.log(`Live view url: ${kernelBrowser.browser_live_view_url}`);
 ```
@@ -43,10 +48,12 @@ const agent = await startBrowserAgent({
     browser: {
         cdp: kernelBrowser.cdp_ws_url,
         contextOptions: {
-            viewport: { width: 1024, height: 768 }
+            viewport: {
+                width: 1920,
+                height: 1080
+            }
         }
     },
-    virtualScreenDimensions: { width: 1024, height: 768 },
     llm: {
         provider: 'anthropic',
         options: {

integrations/overview.mdx

@@ -0,0 +1,30 @@
+---
+title: "Overview"
+---
+
+Kernel's browsers are compatible with all browser and Computer Use frameworks.
+
+## Universal compatibility
+
+Kernel browsers work with any framework or tool that supports the Chrome DevTools Protocol (CDP). This means you can:
+
+- **Use any agent framework**: Integrate with popular frameworks like Browser Use, Stagehand, Playwright, Puppeteer, Selenium, and more
+- **Connect via CDP**: All browsers expose a CDP WebSocket URL for direct connection
+- **No vendor lock-in**: Switch between frameworks or use multiple frameworks simultaneously
+- **Standard protocols**: Built on open standards that work with the entire browser automation ecosystem
+
+## Popular Framework Integrations
+
+Kernel provides detailed guides for popular agent frameworks:
+
+- **[Browser Use](/integrations/browser-use)** - AI browser agent framework
+- **[Stagehand](/integrations/stagehand)** - AI browser automation with natural language
+- **[Computer Use (Anthropic)](/integrations/computer-use/anthropic)** - Claude's computer use capability
+- **[Computer Use (OpenAI)](/integrations/computer-use/openai)** - OpenAI's computer use capability
+- **[Magnitude](/integrations/magnitude)** - Vision-focused browser automation framework
+- **[Val Town](/integrations/valtown)** - Serverless function runtime
+- **[Vercel](https://github.com/onkernel/vercel-template)** - Deploy browser automations to Vercel
+
+## Custom Integrations
+
+Kernel works with any tool that supports CDP. Check out our [browser creation guide](/browsers/create-a-browser) to learn how to connect any other agent framework.