feat: Add Gemini CUA template

index.ts

@@ -20,7 +20,8 @@ type TemplateKey =
   | "advanced-sample"
   | "computer-use"
   | "cua"
-  | "magnitude";
+  | "magnitude"
+  | "gemini-cua";
 type LanguageInfo = { name: string; shorthand: string };
 type TemplateInfo = {
   name: string;
@@ -38,6 +39,7 @@ const TEMPLATE_ADVANCED_SAMPLE = "advanced-sample";
 const TEMPLATE_COMPUTER_USE = "computer-use";
 const TEMPLATE_CUA = "cua";
 const TEMPLATE_MAGNITUDE = "magnitude";
+const TEMPLATE_GEMINI_CUA = "gemini-cua";
 const LANGUAGE_SHORTHAND_TS = "ts";
 const LANGUAGE_SHORTHAND_PY = "py";
 
@@ -86,6 +88,11 @@ const TEMPLATES: Record<TemplateKey, TemplateInfo> = {
     description: "Implements the Magnitude.run SDK",
     languages: [LANGUAGE_TYPESCRIPT],
   },
+  [TEMPLATE_GEMINI_CUA]: {
+    name: "Gemini Computer Use",
+    description: "Implements Gemini 2.5 Computer Use Agent",
+    languages: [LANGUAGE_TYPESCRIPT],
+  },
 };
 
 const INVOKE_SAMPLES: Record<
@@ -104,6 +111,8 @@ const INVOKE_SAMPLES: Record<
       'kernel invoke ts-cua cua-task --payload \'{"task": "Go to https://news.ycombinator.com and get the top 5 articles"}\'',
     [TEMPLATE_MAGNITUDE]:
       'kernel invoke ts-magnitude mag-url-extract --payload \'{"url": "https://en.wikipedia.org/wiki/Special:Random"}\'',
+    [TEMPLATE_GEMINI_CUA]:
+      'kernel invoke ts-gemini-cua gemini-cua-task',
   },
   [LANGUAGE_PYTHON]: {
     [TEMPLATE_SAMPLE_APP]:
@@ -130,6 +139,7 @@ const REGISTERED_APP_NAMES: Record<
     [TEMPLATE_COMPUTER_USE]: "ts-cu",
     [TEMPLATE_CUA]: "ts-cua",
     [TEMPLATE_MAGNITUDE]: "ts-magnitude",
+    [TEMPLATE_GEMINI_CUA]: "ts-gemini-cua",
   },
   [LANGUAGE_PYTHON]: {
     [TEMPLATE_SAMPLE_APP]: "python-basic",
@@ -372,6 +382,8 @@ function printNextSteps(
       ? "kernel deploy index.ts --env ANTHROPIC_API_KEY=XXX"
       : language === LANGUAGE_TYPESCRIPT && template === TEMPLATE_CUA
       ? "kernel deploy index.ts --env OPENAI_API_KEY=XXX"
+      : language === LANGUAGE_TYPESCRIPT && template === TEMPLATE_GEMINI_CUA
+      ? "kernel deploy index.ts --env GOOGLE_API_KEY=XXX --env OPENAI_API_KEY=XXX"
       : language === LANGUAGE_PYTHON &&
         (template === TEMPLATE_SAMPLE_APP ||
           template === TEMPLATE_ADVANCED_SAMPLE)
@@ -415,7 +427,7 @@ program
   )
   .option(
     "-t, --template <template>",
-    `Template type (${TEMPLATE_SAMPLE_APP}, ${TEMPLATE_BROWSER_USE}, ${TEMPLATE_STAGEHAND}, ${TEMPLATE_ADVANCED_SAMPLE}, ${TEMPLATE_COMPUTER_USE}, ${TEMPLATE_CUA}, ${TEMPLATE_MAGNITUDE})`
+    `Template type (${TEMPLATE_SAMPLE_APP}, ${TEMPLATE_BROWSER_USE}, ${TEMPLATE_STAGEHAND}, ${TEMPLATE_ADVANCED_SAMPLE}, ${TEMPLATE_COMPUTER_USE}, ${TEMPLATE_CUA}, ${TEMPLATE_MAGNITUDE}, ${TEMPLATE_GEMINI_CUA})`
   )
   .action(
     async (

templates/typescript/gemini-cua/README.md

@@ -0,0 +1,44 @@
+# Kernel TypeScript SDK + Stagehand + Gemini Computer Use Agent
+
+A Kernel application that demonstrates Computer Use Agent (CUA) capabilities using Google's Gemini 2.5 model with Stagehand for browser automation.
+
+## What It Does
+
+This app uses [Gemini 2.5's computer use model](https://blog.google/technology/google-deepmind/gemini-computer-use-model/) capabilities to autonomously navigate websites and complete tasks. The example task searches for Kernel's company page on YCombinator and writes a blog post about their product.
+
+## Setup
+
+1. **Add your API keys as environment variables:**
+   - `KERNEL_API_KEY` - Get from [Kernel dashboard](https://dashboard.onkernel.com/sign-in)
+   - `GOOGLE_API_KEY` - Get from [Google AI Studio](https://aistudio.google.com/apikey)
+   - `OPENAI_API_KEY` - Get from [OpenAI platform](https://platform.openai.com/api-keys)
+
+## Running Locally
+
+Execute the script directly with tsx:
+
+```bash
+npx tsx index.ts
+```
+
+This runs the agent without a Kernel invocation context and provides the browser live view URL for debugging.
+
+## Deploying to Kernel
+
+1. **Deploy the application:**
+   ```bash
+   kernel deploy index.ts --env GOOGLE_API_KEY=XXX --env OPENAI_API_KEY=XXX
+   ```
+
+2. **Invoke the action:**
+   ```bash
+   kernel invoke ts-gemini-cua gemini-cua-task
+   ```
+
+The action creates a Kernel-managed browser and associates it with the invocation for tracking and monitoring.
+
+## Documentation
+
+- [Kernel Documentation](https://docs.onkernel.com/quickstart)
+- [Kernel Stagehand Guide](https://www.onkernel.com/docs/integrations/stagehand)
+- [Gemini 2.5 Computer Use](https://blog.google/technology/google-deepmind/gemini-computer-use-model/)

templates/typescript/gemini-cua/_gitignore

@@ -0,0 +1,39 @@
+# Dependencies
+node_modules/
+package-lock.json
+
+# TypeScript
+*.tsbuildinfo
+dist/
+build/
+
+# Environment
+.env
+.env.local
+.env.*.local
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Logs
+logs/
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# Testing
+coverage/
+.nyc_output/
+
+# Misc
+.cache/
+.temp/
+.tmp/

templates/typescript/gemini-cua/index.ts

@@ -0,0 +1,125 @@
+import { Stagehand } from "@browserbasehq/stagehand";
+import { Kernel, type KernelContext } from '@onkernel/sdk';
+
+const kernel = new Kernel({
+  apiKey: process.env.KERNEL_API_KEY
+});
+
+const app = kernel.app('ts-gemini-cua');
+
+interface SearchQueryOutput {
+  success: boolean;
+  result: string;
+  error?: string;
+}
+
+// API Keys for LLM providers
+// - GOOGLE_API_KEY: Required for Gemini 2.5 Computer Use Agent
+// - OPENAI_API_KEY: Required for Stagehand's GPT-4o model
+// Set via environment variables or `kernel deploy <filename> --env-file .env`
+// See https://docs.onkernel.com/launch/deploy#environment-variables
+const GOOGLE_API_KEY = process.env.GOOGLE_API_KEY;
+const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
+
+if (!OPENAI_API_KEY) {
+  throw new Error('OPENAI_API_KEY is not set');
+}
+
+if (!GOOGLE_API_KEY) {
+  throw new Error('GOOGLE_API_KEY is not set');
+}
+
+async function runStagehandTask(invocationId?: string): Promise<SearchQueryOutput> {
+  // Executes a Computer Use Agent (CUA) task using Gemini 2.5 and Stagehand
+
+  const browserOptions = {
+    stealth: true,
+    // viewport: {
+    //   width: 1440,
+    //   height: 900,
+    //   refresh_rate: 25
+    // },
+    ...(invocationId && { invocation_id: invocationId })
+  };
+
+  const kernelBrowser = await kernel.browsers.create(browserOptions);
+
+  console.log("Kernel browser live view url: ", kernelBrowser.browser_live_view_url);
+
+  const stagehand = new Stagehand({
+    env: "LOCAL",
+    verbose: 1,
+    domSettleTimeoutMs: 30_000,
+    modelName: "gpt-4o",
+    modelClientOptions: {
+      apiKey: OPENAI_API_KEY
+    },
+    localBrowserLaunchOptions: {
+      cdpUrl: kernelBrowser.cdp_ws_url
+    }
+  });
+  await stagehand.init();
+
+  /////////////////////////////////////
+  // Your Stagehand implementation here
+  /////////////////////////////////////
+  try {
+    const page = stagehand.page;
+
+    const agent = stagehand.agent({
+      provider: "google",
+      model: "gemini-2.5-computer-use-preview-10-2025",
+      instructions: `You are a helpful assistant that can use a web browser.
+      You are currently on the following page: ${page.url()}.
+      Do not ask follow up questions, the user will trust your judgement.`,
+      options: {
+        apiKey: GOOGLE_API_KEY,
+      }
+    });
+
+    // Navigate to YCombinator's website
+    await page.goto("https://www.ycombinator.com/companies");
+
+    // Define the instructions for the CUA agent
+    const instruction = "Find Kernel's company page on the YCombinator website and write a blog post about their product offering.";
+
+    // Execute the instruction
+    const result = await agent.execute({
+      instruction,
+      maxSteps: 20,
+    });
+
+    console.log("result: ", result);
+
+    return { success: true, result: result.message };
+  } catch (error) {
+    console.error(error);
+    const errorMessage = error instanceof Error ? error.message : String(error);
+    return { success: false, result: "", error: errorMessage };
+  } finally {
+    console.log("Deleting browser and closing stagehand...");
+    await stagehand.close();
+    await kernel.browsers.deleteByID(kernelBrowser.session_id);
+  }
+}
+
+// Register Kernel action handler for remote invocation
+// Invoked via: kernel invoke ts-gemini-cua gemini-cua-task
+app.action<void, SearchQueryOutput>(
+  'gemini-cua-task',
+  async (ctx: KernelContext): Promise<SearchQueryOutput> => {
+    return runStagehandTask(ctx.invocation_id);
+  },
+);
+
+// Run locally if executed directly (not imported as a module)
+// Execute via: npx tsx index.ts
+if (import.meta.url === `file://${process.argv[1]}`) {
+  runStagehandTask().then(result => {
+    console.log('Local execution result:', result);
+    process.exit(result.success ? 0 : 1);
+  }).catch(error => {
+    console.error('Local execution failed:', error);
+    process.exit(1);
+  });
+}

templates/typescript/gemini-cua/package.json

@@ -0,0 +1,14 @@
+{
+  "name": "ts-gemini-cua",
+  "module": "index.ts",
+  "type": "module",
+  "private": true,
+  "peerDependencies": {
+    "typescript": "^5"
+  },
+  "dependencies": {
+    "@browserbasehq/stagehand": "^2.5.2",
+    "@onkernel/sdk": "^0.15.0",
+    "zod": "^3.25.67"
+  }
+}

templates/typescript/gemini-cua/tsconfig.json

@@ -0,0 +1,23 @@
+{
+  "compilerOptions": {
+    "lib": ["ESNext", "DOM"],
+    "target": "ESNext",
+    "module": "ESNext",
+    "moduleDetection": "force",
+    "jsx": "react-jsx",
+    "allowJs": true,
+    "moduleResolution": "bundler",
+    "allowImportingTsExtensions": true,
+    "verbatimModuleSyntax": true,
+    "noEmit": true,
+    "strict": true,
+    "skipLibCheck": true,
+    "noFallthroughCasesInSwitch": true,
+    "noUncheckedIndexedAccess": true,
+    "noUnusedLocals": false,
+    "noUnusedParameters": false,
+    "noPropertyAccessFromIndexSignature": false
+  },
+  "include": ["./**/*.ts", "./**/*.tsx"],
+  "exclude": ["node_modules", "dist"]
+}