agents-sdk

Develop, configure and deploy AI agents on Cloudflare Workers with routing and durable execution.

Updated May 1, 2026
One-click install
npx skills add https://github.com/legg/AgentLuhmann --skill agents-sdk-legg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agents-sdk
Source: https://github.com/legg/AgentLuhmann/tree/main/.tessl/tiles/cloudflare/skills/skills/agents-sdk
Command: npx skills add https://github.com/legg/AgentLuhmann --skill agents-sdk-legg

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

The Skill enables developers to create, configure, and deploy feature-rich AI agents within Cloudflare's serverless environment, streamlining automation and integrations.

Core Features & Use Cases

  • Agent Development: Provides classes and APIs to build stateful and stateless agents for various tasks.
  • Communication & Routing: Supports request routing, WebSocket management, and custom URL patterns for scalable deployment.
  • Integration: Facilitates connection to MCP servers, email routing, push notifications, and webhooks to extend agent capabilities.
  • Workflow Automation: Enables durable background tasks, retries, scheduling, and human approval flows for robust automation solutions.
  • Use Case: Example use cases include deploying chatbots, automation tools, data connectors, and monitoring agents that run reliably at scale.

Quick Start

Implement a new agent by extending the Agent class, define fetch routing, and add callable RPC methods to interact with external services or internal logic.

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, extend the base Agent class, define fetch routing, and implement callable RPC methods to handle persistent state and complex task automation.

Can I manage WebSocket connections and webhooks in a serverless agent architecture?

Yes, serverless agent architecture supports WebSocket management, custom URL patterns, and webhooks to enable real-time communication, request routing, and external integrations for scalable deployments.

Does this approach support durable execution for background tasks and retries?

Durable execution is fully supported, enabling robust background task automation, retries, scheduling, and human approval flows to ensure complex workflows run reliably in serverless environments.

How do I connect AI agents to MCP servers and external services?

Connect AI agents to MCP servers and external services by leveraging built-in integration APIs that facilitate email routing, push notifications, and webhook connections to extend agent capabilities.

What is the best way to deploy scalable chatbots and automation tools on serverless infrastructure?

Deploying scalable chatbots and automation tools on serverless infrastructure involves using stateful classes and request routing to manage durable execution and external integrations efficiently at scale.