cloudbase-agent
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.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- cloudbase-agent
- alwaysApply
- true
- 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.
02 资源文件 8
- 参考文档adapter-development.md1.9 KB
- 参考文档adapter-langchain.md2.6 KB
- 参考文档adapter-langgraph.md5.3 KB
- 参考文档agent-deployment.md5.0 KB
- 参考文档agui-protocol.md2.3 KB
- 参考文档server-quickstart.md3.6 KB
- 参考文档ui-clients.md1.3 KB
- 参考文档ui-miniprogram.md4.1 KB
03 SKILL.md 正文
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-functionsskill) - CloudRun backend services without agent features (use
cloudrun-developmentskill)
How to use this skill (for a coding agent)
-
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
-
Deploy the agent server
- Use
@cloudbase/agent-serverto expose HTTP endpoints - Configure CORS, logging, and observability as needed
- Prefer deploying to CloudBase using
manageAgentMCP tool (see agent-deployment) - Before deploy, read Dependency Alignment Policy in agent-deployment to avoid cloud build dependency errors
- Use
-
Build the UI client
- Use
@ag-ui/clientfor web applications - Use
@cloudbase/agent-ui-miniprogramfor WeChat Mini Programs - Connect to the agent server's
/send-messageor/aguiendpoints
- Use
-
Follow the routing table below to find detailed documentation for each task
Routing
| Task | Read |
|---|---|
| Deploy agent to CloudBase (read this first) | agent-deployment |
| Deploy agent server (@cloudbase/agent-server) | server-quickstart |
| Use LangGraph adapter | adapter-langgraph |
| Use LangChain adapter | adapter-langchain |
| Build custom adapter | adapter-development |
| Understand AG-UI protocol | agui-protocol |
| Build UI client (Web or Mini Program) | ui-clients |
| Deep-dive @cloudbase/agent-ui-miniprogram | ui-miniprogram |
Quick Start
Prerequisites: Node.js >= 20 is required.
1. Install dependencies:
npm install @cloudbase/agent-server@latest @cloudbase/agent-adapter-langgraph@latest
Critical: Always use @latest for all @cloudbase/agent-* packages. For dependency version rules, see Dependency Alignment Policy in agent-deployment.md.
2. Create and run your agent:
import { run } from "@cloudbase/agent-server";
import { LanggraphAgent } from "@cloudbase/agent-adapter-langgraph";
run({
createAgent: () => ({ agent: new LanggraphAgent({ workflow }) }),
port: 9000,
});
04 同仓库更多 Skills
vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.