Contains two packages, packages/agent and packages/web, responsible for the browser agent and the chat interface respectively
vercel-example — Next.js Starter Template
By kernel
A Vercel example template provided by Kernel, containing a Next.js-based chat interface and a browser automation agent deployed on Kernel, used to build an AI chatbot that can control a browser.
Explore the design
Compare the page layouts and mobile experience. Open any screenshot for a closer look.
Actual screenshot captured by the server browser.
All pages & views 3
Screenshots show visual appearance; interactive behavior may differ.
What stands out
A quick read of the recorded project description.
The web package uses Next.js, Vercel AI SDK, and Assistant-UI to build the chat interface
The agent is deployed as an action in a Kernel application and runs the Claude Computer Use Playwright SDK to control the browser
The chatbot is deployed as a route in the web application and controls the browser through browserAgentTool
The README explains that the web application can be deployed to Vercel and notes that Vercel Functions have runtime duration limits
Template Details
This template is an example chatbot with browser automation capabilities, and the repository is divided into two packages: packages/agent and packages/web. The web package uses Next.js, Vercel AI SDK, and Assistant-UI to build the chat interface; the chatbot is deployed as a route in the web application and controls the browser through browserAgentTool. The agent package is deployed as an action in a Kernel application and runs the Claude Computer Use Playwright SDK to operate the browser. The README provides steps from registering a Kernel account, obtaining an API key, cloning the repository, installing the Kernel CLI, and configuring environment variables, to deploying the agent and starting the web development server, and explains that the web application can be deployed to Vercel. The README does not describe the template's performance, production readiness, or any features beyond the above.
Is it right for your project?
Use Cases
- Building an example AI chatbot that can control a browser
- Deploying and running a browser automation agent on Kernel
- Deploying the chat interface to Vercel and connecting it to the agent on Kernel
- Extending the template with custom tools and a chatbot
Suitable For
- Developers who want to understand how Kernel and Vercel work together
- Developers who need a reference implementation of a browser automation chatbot
- Developers building chat interfaces with Next.js and Vercel AI SDK
Getting started & customization
Use these recorded setup notes alongside the repository instructions for your chosen version.
- 1
Register a Kernel account and create an API key
- 2
After cloning the repository, copy .env.example to .env in the packages/agent and packages/web directories respectively, and fill in KERNEL_API_KEY and ANTHROPIC_API_KEY
- 3
Install the Kernel CLI via brew install onkernel/tap/kernel
- 4
Run pnpm run deploy:agent to deploy the agent to Kernel
- 5
Run pnpm run dev:web to start the web development server and visit http://localhost:3000
License & source material
Usage conditions & limitations
Free to use · keep license noticeThis entry covers the free version under the MIT license in the public repository; the free scope is the code of this version and does not mean that external services or third-party assets are free.
Must comply with when using
- Free use, modification, commercial use, and distribution of this version's code are permitted.
- When distributing copies or substantial portions of the code, retain the original author's copyright notice and the complete MIT license notice.
- The code is provided as is; warranties and limitations of liability are governed by the original license and applicable law.
Additional costs & items to verify
- Demo images, fonts, icons, and other third-party assets must be checked against their respective licenses and cannot be judged solely by the code's MIT license.
- External services such as domains, hosting, databases, payments, or AI may incur separate charges.
- Before use, you must register a Kernel account and create an API key, which is an external service account requirement.
- The Kernel API key and Anthropic API key need to be configured in the .env files of packages/agent and packages/web; without the keys, it cannot run.
- The agent must first be deployed to the Kernel platform before the web application can work properly.
- Before deploying to Vercel, ensure that the AI web agent has been deployed to Kernel according to Getting Started.
- Vercel Functions have runtime duration limits, and long tasks may time out due to Vercel settings.
View Original Text Basis
Permission is hereby granted, free of charge
Original License Text
1. Sign up for a [Kernel account](https://dashboard.onkernel.com/sign-up) and create an API key.
Original README
4. Add your Kernel API key and Anthropic API key to the `.env` file in the `packages/agent` and `packages/web` directories.
Original README
5. Deploy the agent to Kernel:
Original README
You can deploy the web app on Vercel. Make sure you've also deployed the AI web agent on Kernel as described in the Getting Started section.
Original README
https://github.com/kernel/vercel-example/blob/main/LICENSEhttps://github.com/kernel/vercel-example/blob/main/README.mdVercel Functions have [limits](https://vercel.com/docs/functions/configuring-functions/duration) on how long they can run. Configure the app's [here](https://github.com/onkernel/vercel-template/blob/56656ccd6f6d5de084f29974d03ea4f88c35cf84/packages/web/app/api/chat/route.ts#L11). Long-running tasks may time out depending on your Vercel settings.
Original README
Compiled by DeepSeek based on repository license and README ·2026-10-14. Results only cover the materials read; dependencies, images, fonts, and subsequent term changes are subject to their respective original texts.
Project checks & description sources
Template Information
- Source platforms
- GitHub
- Documentation and maintenance reference score
- More documented · 77 / 100
- Technologies
- Next.js · React
- Website type
- Starter
How this score is calculated
Our heuristic uses license records (up to 30), a demo link (12), a preview (10), stars (15), recorded maintenance (15), description completeness (8), feature records (5) and classification data (5). It is not a code, security or performance test, or a Google score. A link does not establish tested functionality.
What to verify for this project
- Repository update recorded
- 2025-10-16
- Screenshot last checked
- 2026-10-14
A demo link is listed. Check it with your own content and viewport sizes; its presence does not confirm that forms, authentication or payments work.
The catalog identifies Next.js as the primary stack. Check the actual dependency manifest and lockfile for versions and hosting requirements. These notes use recorded metadata, not a code audit or a deployment test.
Use a selection guide →How this description was prepared
AI-assisted description based on catalog records and repository material. Repository authors are not automatically the reviewers of this description.
Review declaration: codex-user-requested-batch-review-20261015 · 2026-10-15
Inspect the recorded source material
SHA-256: 088c1672f310730ab4b1ccee2f5b6e24ffdd27e0a92f3ba0217cb6aa3077108a
2026-10-14T08:40:10.471Z
Source file / repository<p align="center"> <img src="static/images/kernel_wordmark.svg" alt="Kernel Logo" width="55%"> </p> <p align="center"> <img alt="GitHub License" src="https://img.shields.io/github/license/onkernel/vercel-template"> <a href="https://discord.gg/FBrveQRcud"><img src="https://img.shields.io/discord/1342243238748225556?logo=discord&logoColor=white&color=7289DA" alt="Discord"></a> <a href="https://x.com/onkernel"><img src="https://img.shields.io/twitter/follow/onkernel" alt="Follow @onkernel"></a> </p> # Kernel Vercel Example A chatbot template with browser automation capabilities. Uses [Next.js](https://nextjs.org/), [Vercel AI SDK](https://ai-sdk.dev), [Assistant-UI](https://github.com/assistant-ui/assistant-ui), and [Kernel](https://www.onkernel.com). <p align="center"> <img src="https://github.com/user-attachments/assets/c7b212a6-8872-4c82-8f1d-92c9021eb393" alt="kernel-vercel-template"> </p> ## Getting Started 1. Sign up for a [Kernel account](https://dashboard.onkernel.com/sign-up) and create an API key. 2. Clone the repository: ```bash git clone https://github.com/onkernel/vercel-template.git cd vercel-template ``` 3. Download the Kernel CLI: ```bash brew install onkernel/tap/kernel ``` 4. Add your Kernel API key and Anthropic API key to the `.env` file in the `packages/agent` and `packages/web` directories. ```bash cd packages/agent && cp .env.example .env cd ../web && cp .env.example .env # In .env KERNEL_API_KEY=your-api-key ANTHROPIC_API_KEY=your-api-key ``` 5. Deploy the agent to Kernel: ```bash pnpm run deploy:agent ``` 6. Run the development server for the web app: ```bash pnpm run dev:web ``` You can now access the web app at `http://localhost:3000` ## Deploying to Vercel You can deploy the web app on Vercel. Make sure you've also deployed the AI web agent on Kernel as described in the Getting Started section. [](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fonkernel%2Fvercel-template%2Ftree%2Fmain%2Fpackages%2Fweb&env=KERNEL_API_KEY&env=ANTHROPIC_API_KEY&envDescription=API%20keys%20needed%20for%20the%20application.&envLink=https%3A%2F%2Fdashboard.onkernel.com%2Fsign-up&project-name=web-agent-app) Vercel Functions have [limits](https://vercel.com/docs/functions/configuring-functions/duration) on how long they can run. Configure the app's [here](https://github.com/onkernel/vercel-template/blob/56656ccd6f6d5de084f29974d03ea4f88c35cf84/packages/web/app/api/chat/route.ts#L11). Long-running tasks may time out depending on your Vercel settings. ## Project Layout ```bash kernel-vercel-template/ ├── packages/ │ ├── agent/ # Kernel browser agent │ ├── web/ # Next.js web app ``` ### `packages/agent` The agent is deployed as an [action](https://docs.onkernel.com/info/concepts#action) in your Kernel app. The action runs our [Claude Computer Use Playwright SDK](https://github.com/onkernel/cu-playwright-ts) to control the browser. You can tail the logs of the action by running `pnpm run logs` in the `packages/agent` directory. ### `packages/web` The web app is responsible for the UI. It uses [Next.js](https://nextjs.org/), Vercel [AI SDK](https://ai-sdk.dev), and [Assistant-UI](https://github.com/assistant-ui/assistant-ui) to build the chat interface. The chatbot is deployed as a [route](packages/web/app/api/chat/route.ts) in the web app and uses the `browserAgentTool` to control the browser. You can extend this to build a custom chatbot with your own tools. ## What's Kernel? Kernel provides hosted browsers on-demand for browser automations and web agents. You can connect to the browser using Chrome DevTools-based browser frameworks (Playwright, Puppeteer). ### What You Can Do With Kernel - Run automated browser-based workflows - Develop and test AI agents that use browsers - Build custom tools that require controlled browser environments ## Support For issues, questions, or feedback, please [open an issue](https://github.com/onkernel/vercel-template/issues) on this repository. You can also join our [Discord](https://discord.gg/FBrveQRcud). ## License See the [LICENSE](./LICENSE) file for details. ## Colophon The background wallpaper was generated by AI. Made with ❤️ by the [Kernel team](https://www.onkernel.com).
Explore similar templates
Compare previews and descriptions within the same stack and category.

Next.js SaaS Starter
The official Next.js SaaS starter template, integrating email/password authentication, Stripe Checkout subscriptions, a dashboard with user/team CRUD, basic Owner/Member RBAC, and activity logging.
Next.js · SaaS

Next.js Commerce
Vercel's officially maintained Next.js App Router ecommerce starter with deep Shopify integration, offering a complete product catalog, cart, and checkout flow. Core logic is modular for swapping backends, and community provider versions exist for BigCommerce, Medusa, and Saleor.
Next.js · E-commerce

Next-js-Boilerplate
A developer-first Next.js 16 starter with Tailwind CSS 4 and TypeScript, supporting both App Router and Page Router.
Next.js · Starter

tailwind-nextjs-starter-blog
A Next.js and Tailwind CSS blog starter template using Contentlayer for Markdown/MDX, with built-in SEO, code highlighting, and tags. It targets personal technical blogs and migration from Jekyll/Hugo to React, and supports one-click Vercel deployment.
Next.js · Blog

next-forge
next-forge is a Turborepo-based Next.js template maintained by Vercel, positioned as a starting point for SaaS products.
Next.js · Starter

SaaS-Boilerplate
SaaS-Boilerplate is an open-source SaaS starter template built with Next.js App Router, React 19, TypeScript, Tailwind CSS, and Shadcn UI.
Next.js · SaaS
