agents-sdk

Develop AI agents on Cloudflare Workers with state management and WebSockets.

5|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/lidge-jun/cli-jaw-skills --skill agents-sdk-lidge-jun
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agents-sdk
Source: https://github.com/lidge-jun/cli-jaw-skills/tree/main/agents-sdk
Command: npx skills add https://github.com/lidge-jun/cli-jaw-skills --skill agents-sdk-lidge-jun

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a robust framework for building stateful, real-time AI agents and applications on Cloudflare Workers, simplifying complex tasks like real-time chat, durable workflows, and state management.

Core Features & Use Cases

  • Agent Development: Build agents with persistent state, callable RPC methods, and scheduling capabilities.
  • Durable Workflows: Implement long-running background tasks, human-in-the-loop approvals, and multi-step pipelines.
  • Real-time Applications: Create chat applications, WebSocket apps, and MCP servers.
  • Use Case: Develop a customer support bot that maintains conversation history, handles complex multi-turn interactions, and can trigger background processes for user requests.

Quick Start

Use the agents-sdk skill to create a new agent named 'MyChatAgent' that handles real-time chat.

Frequently Asked Questions about agents-sdk

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build stateful AI agents on Cloudflare Workers?▼

To build stateful AI agents on Cloudflare Workers, you can use this SDK to implement persistent state management, callable RPC methods, and scheduling capabilities without external state stores.

How do I maintain conversation history for a real-time chat agent?▼

Maintaining conversation history for a real-time chat agent is handled via the SDK's built-in state management, allowing agents to preserve context across multi-turn WebSocket interactions.

Can I run durable workflows and human-in-the-loop approvals on Cloudflare Workers?▼

Yes, you can run durable workflows and human-in-the-loop approvals on Cloudflare Workers using this framework to manage long-running background tasks and multi-step pipelines.

Does this SDK support building MCP servers for AI applications?▼

Yes, this SDK supports building MCP servers, enabling real-time communication and integration with external services for complex AI-powered applications on Cloudflare Workers.

What is the best way to implement real-time communication for AI agents on edge networks?▼

The best way to implement real-time communication for AI agents on edge networks is using this SDK's WebSocket support, which facilitates interactive and resilient services on Cloudflare Workers.