> For the complete documentation index, see [llms.txt](https://docs.vapinetwork.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.vapinetwork.ai/agents/quickstart.md).

# Run your first agent

Agents is coming soon; this launch guide covers creating, linking, funding, and running a local agent with limits.

{% hint style="info" %}
Agents is coming soon. This page describes how it works at launch.
{% endhint %}

This guide is for owners who want to create, link, fund, and run one local agent with clear limits.

New to vAPI? Start with the [Quickstart](https://docs.vapinetwork.ai/quickstart). Read [How wallets work](/agents/wallets/how-wallets-work.md) before you fund the agent.

## 1. Install and initialize

Install the client globally:

```bash
npm i -g vapi-network
```

Or skip the global install and initialize through `npx`:

```bash
npx vapi-network init
```

If you installed globally, initialize with the shorter command:

```bash
vapi init
```

The remaining examples use the global `vapi` command. If you skipped the global install, replace it with `npx vapi-network`.

## 2. Create the agent

Create `researcher.md` with the agent's instructions:

```md
Find current, verifiable data. Prefer primary sources, cite every factual claim, and explain when the available evidence is incomplete.
```

Create a `researcher` agent. The wallet cap and suggested Router allowance are daily limits shared by its runs:

```bash
vapi agent create researcher \
  --model openai/gpt-5-mini \
  --instructions researcher.md \
  --call-budget 2 \
  --router-budget 2
```

The client creates the local profile and its dedicated wallet.

## 3. Approve the link

The terminal shows a code and a URL. Open `https://api.vapinetwork.ai/link?code=...`, approve the link with your wallet, and set the daily Router allowance. The code lasts 20 minutes.

The code links the agent wallet to your account. It does not give the agent control of your wallet.

## 4. Fund the agent wallet

Open the funding page and print the agent's address:

```bash
vapi fund --account researcher --amount 2
```

Send USDC on Base to the printed address.

Buy $1 of Router balance so the first model call does not depend on the owner having Compute:

```bash
vapi router buy 1 --account researcher
```

The purchase uses the agent wallet's USDC and counts against its daily wallet cap. The remaining USDC can pay for vAPI Call requests.

## 5. Run a task

Run the agent on your machine:

```bash
vapi agent run researcher "Summarise today's Base DEX volume with sources"
```

## 6. Check the agent

Open **My agents** at `/agents` in the console. The `researcher` entry is the owner link for the local wallet, not a hosted agent process.

List local agent profiles and today's budgets:

```bash
vapi agent list
```

Check the account link and permissions for the wallet:

```bash
vapi whoami --account researcher
```

## Next

* [Limits and ceilings](/agents/wallets/limits-and-ceilings.md)
* [Owner and agents](/agents/control/owner-and-agents.md)
* [CLI reference](https://docs.vapinetwork.ai/reference/cli/cli-reference)

Checked on 2026-10-02.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.vapinetwork.ai/agents/quickstart.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.