# Hono — Ultrafast Web Framework for the Edge

> Tiny, fast web framework for Cloudflare Workers, Deno, Bun, and Node.js. Perfect API layer for AI services. 29K+ GitHub stars.

## Install

Save as a script file and run:

# Hono — Ultrafast Web Framework for the Edge

## Quick Use

```bash
npm create hono@latest my-api
cd my-api && npm install && npm run dev
```

```typescript
import { Hono } from 'hono';

const app = new Hono();

app.get('/', (c) => c.text('Hello Hono!'));

app.post('/api/chat', async (c) => {
    const { prompt } = await c.req.json();
    const response = await fetch('https://api.openai.com/v1/chat/completions', {
        method: 'POST',
        headers: {
            'Authorization': `Bearer ${c.env.OPENAI_API_KEY}`,
            'Content-Type': 'application/json',
        },
        body: JSON.stringify({
            model: 'gpt-4o',
            messages: [{ role: 'user', content: prompt }],
        }),
    });
    return c.json(await response.json());
});

export default app;
```

Deploy to Cloudflare Workers:
```bash
npx wrangler deploy
```

---

## Intro

Hono is an ultrafast, lightweight web framework with 29,700+ GitHub stars built on Web Standards. It runs everywhere — Cloudflare Workers, Deno, Bun, Node.js, AWS Lambda, Vercel — making it the ideal API layer for AI services that need low latency and global distribution. With zero dependencies, built-in middleware (CORS, auth, rate limiting), OpenAPI schema generation, and RPC-style type-safe clients, Hono lets you build production AI APIs in minutes. At ~14KB, it starts in under 1ms on edge runtimes.

Works with: Cloudflare Workers, Deno, Bun, Node.js, AWS Lambda, Vercel Edge, any OpenAI/Anthropic API. Best for developers building low-latency AI API endpoints at the edge. Setup time: under 2 minutes.

---

## Hono Features

### Multi-Runtime Support

| Runtime | Command |
|---------|--------|
| **Cloudflare Workers** | `npx wrangler deploy` |
| **Deno** | `deno serve app.ts` |
| **Bun** | `bun run app.ts` |
| **Node.js** | `node app.js` |
| **AWS Lambda** | Deploy via SAM/CDK |
| **Vercel Edge** | Deploy via Vercel CLI |

### Built-in Middleware

```typescript
import { Hono } from 'hono';
import { cors } from 'hono/cors';
import { bearerAuth } from 'hono/bearer-auth';
import { rateLimiter } from 'hono/rate-limiter';

const app = new Hono();

app.use('/api/*', cors());
app.use('/api/*', bearerAuth({ token: 'my-secret-token' }));
```

### AI Streaming Responses

```typescript
import { Hono } from 'hono';
import { streamSSE } from 'hono/streaming';

app.post('/api/stream', async (c) => {
    return streamSSE(c, async (stream) => {
        const response = await fetch('https://api.openai.com/v1/chat/completions', {
            method: 'POST',
            headers: { 'Authorization': `Bearer ${c.env.OPENAI_API_KEY}` },
            body: JSON.stringify({ model: 'gpt-4o', messages: [...], stream: true }),
        });

        const reader = response.body.getReader();
        while (true) {
            const { done, value } = await reader.read();
            if (done) break;
            await stream.writeSSE({ data: new TextDecoder().decode(value) });
        }
    });
});
```

### OpenAPI Schema Generation

```typescript
import { OpenAPIHono, createRoute, z } from '@hono/zod-openapi';

const route = createRoute({
    method: 'post',
    path: '/api/chat',
    request: { body: { content: { 'application/json': { schema: z.object({ prompt: z.string() }) } } } },
    responses: { 200: { description: 'Chat response' } },
});

app.openapi(route, (c) => { /* handler */ });
app.doc('/docs', { openapi: '3.0.0', info: { title: 'AI API', version: '1.0' } });
```

### Performance

- **~14KB** bundle size (zero dependencies)
- **<1ms** cold start on edge runtimes
- **150K+ req/s** on Bun benchmarks
- Built on Web Standards (Request/Response)

---

## FAQ

**Q: What is Hono?**
A: Hono is an ultrafast web framework with 29,700+ GitHub stars that runs on Cloudflare Workers, Deno, Bun, Node.js, and more. ~14KB, <1ms cold start, built-in middleware, ideal for AI API endpoints.

**Q: Why use Hono for AI services?**
A: AI APIs need low latency and global distribution. Hono runs at the edge (Cloudflare Workers) with <1ms cold start, has built-in SSE streaming for LLM responses, and includes auth/CORS/rate-limiting middleware out of the box.

**Q: Is Hono free?**
A: Yes, open-source under MIT license.

---

## Source & Thanks

> Created by [Yusuke Wada](https://github.com/honojs). Licensed under MIT.
>
> [hono](https://github.com/honojs/hono) — ⭐ 29,700+

---

<!-- ZH -->

## 快速使用

```bash
npm create hono@latest my-api
cd my-api && npm run dev
```

---

## 简介

Hono 是一个拥有 29,700+ GitHub stars 的超快 Web 框架，运行在 Cloudflare Workers、Deno、Bun、Node.js 等多个运行时。~14KB 体积，<1ms 冷启动，内置中间件，是构建 AI API 端点的理想选择。

---

## 来源与感谢

> Created by [Yusuke Wada](https://github.com/honojs). Licensed under MIT.
>
> [hono](https://github.com/honojs/hono) — ⭐ 29,700+


---
Source: https://tokrepo.com/en/workflows/ff72c952-86a4-402d-b288-7468b3a3f4c5
Author: Script Depot