# Cloudbase Agent

Build and deploy AI agents with Cloudbase Agent (TypeScript), a TypeScript SDK...

- Repository: https://github.com/TencentCloudBase/CloudBase-AI-Toolkit (1153 stars)
- Category: Design
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill cloudbase-agent -g -a claude-code -y`
Codex: `npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill cloudbase-agent -g -a codex -y`
Cursor: `npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill cloudbase-agent -g -a cursor -y`
Gemini CLI: `npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill cloudbase-agent -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add TencentCloudBase/CloudBase-AI-Toolkit`

## Description

Build and deploy AI agents with Cloudbase Agent (TypeScript), a TypeScript SDK implementing the AG-UI protocol. Use when: (1) deploying agent servers with @cloudbase/agent-server, (2) using LangGraph adapter with ClientStateAnnotation, (3) using LangChain adapter with clientTools(), (4) building custom adapters that implement AbstractAgent, (5) understanding AG-UI protocol events, (6) building web UI clients with @ag-ui/client, (7) building WeChat Mini Program UIs with @cloudbase/agent-ui-miniprogram.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# 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)

1. **Choose the right adapter**
   - Use LangGraph adapter for stateful, graph-based workflows
   - Use LangChain adapter for chain-based agent patterns
   - Build custom adapter for specialized agent logic

2. **Deploy the agent server**
   - Use `@cloudbase/agent-server` to expose HTTP endpoints
   - Configure CORS, logging, and observability as needed
   - **Prefer deploying to CloudBase using `manageAgent` MCP tool** (see [agent-deployment](agent-deployment.md))
   - **Before deploy, read Dependency Alignment Policy in [agent-deployment](agent-deployment.md) to avoid cloud build dependency errors**

3. **Build the UI client**
   - Use `@ag-ui/client` for web applications
   - Use `@cloudbase/agent-ui-miniprogram` for WeChat Mini Programs
   - Connect to the agent server's `/send-message` or `/agui` endpoints

4. **Follow the routing table below** to find detailed documentation for each task

## Routing

The rest: https://github.com/TencentCloudBase/CloudBase-AI-Toolkit/blob/HEAD/config/.claude/skills/cloudbase-agent/ts/SKILL.md