Build a working agent app on your machine with a direct model provider. This tutorial does not require a Veryfront account or Veryfront Cloud.
Prerequisites
- Node.js 22.3 or later.
- An OpenAI API key for model inference.
Create the app
npm create veryfront@latest support-agent -- --template ai-agent
cd support-agentThe starter contains an assistant agent, calculator.ts tool, chat page,
AG-UI route, and smoke eval.
Answer No to Use Veryfront Cloud? to follow this direct-provider tutorial. To use Veryfront inference and inspect local runs in Studio without a provider API key, follow the Cloud quickstart.
Configure inference
Set the API key in the terminal where you run Veryfront:
export OPENAI_API_KEY="<API_KEY>"The starter uses openai/gpt-5-nano. Veryfront sends the requests directly
to OpenAI.
Run the app
npm run devThe CLI confirms the server and available inference path:
✓ App ready http://localhost:3000
Execution This machine
Inference OpenAI directVerify it worked
Open the local URL printed by the CLI and ask:
What is 128 divided by 8?The assistant calls the calculator tool and returns 16.
Run the eval
Stop the dev server with Ctrl+C, then run:
npm run eval -- assistantThe command exits successfully after the agent calls the calculator and returns the expected answer.
Add local delegation
Continue with Local delegation when you need more than one agent.
Next steps
- Add tools to give the agent another capability.
- Write evaluations to ensure changes preserve expected behavior.
- Deploy with Cloud or Self-host the app.
Use another inference provider when you need a different model or local inference.