一个代理聊天运行时的原型，以 markdown 为协议。LLM 流式 markdown 文本，执行 TypeScript 代码，在服务器端阻挡，并在客户端渲染反应式 UI 组件——全部在单一响应中完成。

论点： Markdown 是代理型人工智能助手的理想协议。它是大型语言模型已经理解的，将散文、可执行代码和结构化数据混合，格式无需新训练。

📖 **阅读附带文章：**智能人工智能助手的未来是…Markdown

Docker 快速入门

在浏览器中打开http://localhost:4000。

环境变量

地方发展

先决条件

• 面包>= 1.0

布置

谷歌技能（邮件、日历、联系人）

邮件、日历和联系人技能需要Google OAuth凭证。没有这些，可以在你的’中设置FENCED_DISABLE_GOOGLE_SKILLS=true。

fenced

A prototype of an agentic chat runtime where markdown is the protocol. The LLM streams markdown text, executes TypeScript code blocks server-side, and renders reactive UI components on the client—all within a single response.

Thesis: Markdown is the ideal protocol for agentic AI assistants. It’s what LLMs already understand, mixing prose, executable code, and structured data in a format that requires no new training.

📖 Read the accompanying article: The Future of Agentic AI Assistants Is… Markdown

Quick Start with Docker

# Build the image
docker build -t fenced .

# Run with required environment variables
docker run -p 4000:4000 \
  -e OPENAI_API_KEY=your-openai-api-key \
  -e FENCED_DISABLE_GOOGLE_SKILLS=true \
  fenced

Open http://localhost:4000 in your browser.

Environment Variables

Local Development

Prerequisites

• Bun >= 1.0

Setup

# Install dependencies
bun install

# Create .env file
cp .env.example .env
# Edit .env with your OPENAI_API_KEY

# Run dev servers (two terminals)
bun run dev:server   # Bun API on port 4000
bun run dev:client   # Vite dev server with HMR

# Or use tmux to run both
bun run dev

Google Skills (Mail, Calendar, Contacts)

The mail, calendar, and contacts skills need Google OAuth credentials. Without them, set FENCED_DISABLE_GOOGLE_SKILLS=true in your .env to skip loading these skills.

1. Create OAuth credentials:

1. Go to Google Cloud Console
2. Create a project (or select an existing one)
3. Enable the Gmail API, Google Calendar API, and People API
4. Configure the OAuth consent screen (External, add your email as test user)
5. Under Credentials → Data Access, add these scopes:
   • https://www.googleapis.com/auth/gmail.modify
   • https://www.googleapis.com/auth/calendar
   • https://www.googleapis.com/auth/contacts
6. Go to Credentials → Create Credentials → OAuth client ID
7. Choose Desktop app as the application type
8. Download the JSON and save it as:

   packages/skills/src/google-auth/client_secret.json
   

2. Generate access token:

bun run google:renew-token

This starts a local server on port 3000, opens your browser for OAuth consent, and saves the token to token.json.

3. Verify it works:

bun run google:test-auth

4. Done. The agent can now use gmail, calendar, and contacts globals in agent.run blocks.