Quickstart
Turn your A2A Agents into an agent-native application in 10 minutes.
Build agents that get smarter with every use.
Rich Threads keep messages, generative UI, and tool activity available across sessions and devices.
Learning turns real usage into skills that improve your agent.
Build a new agent or bring one you already have. Any frontend, any backend.
Prerequisites#
Before you begin, you'll need the following:
- A Google Gemini API key
- Node.js 20+
- Python 3.9+
- Your favorite package manager
Getting started#
Create a free account#
Sign up for a free developer account for CopilotKit Intelligence to get a license key. You'll use it later to enable persistent threads and the inspector.
Clone the A2A starter template#
git clone https://github.com/copilotkit/with-a2a-a2ui.gitInstall dependencies#
pnpm installConfigure your environment#
Create a .env file in your agent directory and add your Google API key:
GEMINI_API_KEY=your_gemini_api_keyWhat about other models?
The starter template is configured to use Google's Gemini by default, but you can modify it to use any language model supported by ADK.
Start the development server#
npm run devpnpm devyarn devbun devThis will start both the UI and agent servers concurrently.
🎉 Start chatting!#
Your AI agent is now ready to use! Navigate to localhost:3000 and start prompting it:
Show me chinese restaurants in NYCTroubleshooting
- If you're having connection issues, try using
0.0.0.0or127.0.0.1instead oflocalhost - Make sure your agent is running on port 10002
- Check that your Google API key is correctly set
Open Inspector and confirm setup#
On localhost, click the Inspector button in the corner of the app.
- Open Agents, then Agent. Your agent is listed.
- Send a chat message. Open Agents, then AG-UI Events. Events are moving.
- Open Threads. The list is unlocked (Intelligence is on), or locked with Enable Intelligence (Intelligence is off).
More detail: Inspector.
What's next?#
Now that you have your basic agent setup, explore these advanced features: