cloudbase-agent-ts（云基 Agent ts）

Cloudbase Agent (TypeScript)

TypeScript SDK for deploying AI agents as HTTP services using the AG-UI protocol.

Note: This skill is for TypeScript/JavaScript projects only.

When to use this skill

Use this skill for AI agent development when you need to:

• Deploy AI agents as HTTP services with AG-UI protocol support
• Build agent backends using LangGraph or LangChain frameworks
• Create custom agent adapters implementing the AbstractAgent interface
• Understand AG-UI protocol events and message streaming
• Build web UI clients that connect to AG-UI compatible agents
• Build WeChat Mini Program UIs for AI agent interactions

Do NOT use for:

• Simple AI model calling without agent capabilities (use ai-model-* skills)
• CloudBase cloud functions (use cloud-functions skill)
• CloudRun backend services without agent features (use cloudrun-development skill)

How to use this skill (for a coding agent)

MUST READ: Read ALL docs that match your task

Before writing any code, identify which docs you need and read ALL of them. Reading only a subset leads to incomplete implementations (missing CORS, wrong adapter patterns, no UI client code).

Scenario-based reading lists

Step-by-step workflow

1. Identify the adapter type from the task description (LangGraph / LangChain / custom)
2. Read the matching docs from the table above — read ALL listed docs, not just one
3. Set up the agent server using @cloudbase/agent-server — always include cors: true
4. Implement the agent logic using the chosen adapter
5. If building UI, read ui-clients.md and create the client code

Reference doc index

Quick Start

import { run } from "@cloudbase/agent-server";
import { LanggraphAgent } from "@cloudbase/agent-adapter-langgraph";

run({
  createAgent: () => ({ agent: new LanggraphAgent({ workflow }) }),
  port: 9000,
});