> ## Documentation Index
> Fetch the complete documentation index at: https://kenpachi.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Build a tool-using agent in under 5 minutes.

This guide covers the three patterns you'll use most: plain chat, tools, and streaming.

***

## 1. Plain chat (no tools)

```typescript theme={null}
import { Agent, createAnthropicProvider } from "kenpachi";

const provider = createAnthropicProvider({
  apiKey: process.env.ANTHROPIC_API_KEY!,
  model: "claude-sonnet-4-6",
});
const agent = new Agent(provider, []);

const result = await agent.run("Write a one-sentence greeting.");
console.log(result.text);
```

`agent.run()` loops until the model stops calling tools and returns final text. For chat-only agents, pass an empty tools array.

***

## 2. Agent with a tool

Define a tool with `defineTool`, pass it to the agent, and ask a question that requires it:

```typescript theme={null}
import { z } from "zod";
import { Agent, defineTool, createAnthropicProvider } from "kenpachi";

const getWeather = defineTool({
  name: "get_weather",
  description: "Get current weather for a city",
  schema: z.object({
    city: z.string().describe("City name"),
  }),
  async execute({ city }) {
    // Replace with your real API call
    return { city, tempC: 24, condition: "sunny" };
  },
});

const provider = createAnthropicProvider({
  apiKey: process.env.ANTHROPIC_API_KEY!,
  model: "claude-sonnet-4-6",
});
const agent = new Agent(provider, [getWeather]);

const result = await agent.run("What's the weather in Nashik?");
console.log(result.text);
// → "It's sunny and 24°C in Nashik."
```

kenpachi handles the full loop: model calls `get_weather` → your `execute` runs → result goes back to the model → model writes the final answer.

***

## 3. Stream text to your UI

Add `onText` to show tokens as they arrive:

```typescript theme={null}
process.stdout.write("Agent: ");

const result = await agent.run("Tell me a fun fact about Nashik", {
  onText: (chunk) => process.stdout.write(chunk),
});

process.stdout.write("\n");
```

See [Streaming](/concepts/streaming) for the full event API (`agent.stream()`).

***

## What's next?

<CardGroup cols={2}>
  <Card title="Handoffs" icon="arrows-turn-right" href="/concepts/handoffs">
    Delegate to billing, support, or other specialist agents.
  </Card>

  <Card title="Time-travel context" icon="clock-rotate-left" href="/concepts/state-checkpointing">
    Undo, edit, or branch conversations without extra API cost.
  </Card>

  <Card title="Schema Validation & Coercion" icon="wand-magic-sparkles" href="/concepts/schema-validation-recovery">
    Recover when the model sends bad tool arguments.
  </Card>

  <Card title="Agent API" icon="book" href="/api-reference/agent">
    Full reference for run(), stream(), and options.
  </Card>
</CardGroup>