Build stateful AI agents on Cloudflare Workers using the Agents SDK.
npx skills add https://github.com/aashahin/ai-skills --skill agents-sdk-aashahin
Please help me install this Agent Skill. Skill: agents-sdk Source: https://github.com/aashahin/ai-skills/tree/main/agents-sdk Command: npx skills add https://github.com/aashahin/ai-skills --skill agents-sdk-aashahin
setState, and @callable RPC methods over WebSocket. - Durable Background Work: Run Workflows, durable fibers, FIFO queues, retries with backoff, and cron/interval scheduling that survive Durable Object eviction. - Chat, MCP & Integrations: Build streaming chat agents with AIChatAgent, connect to or build MCP servers, handle email, webhooks, push notifications, and experimental voice/browser tools. - Use Case: Build a customer support chat agent that persists conversation history, schedules follow-up reminders, calls MCP tools, and streams responses to a React client with resumable streaming. ## Quick Start Ask the AI to create a Cloudflare Worker agent class with persistent state and a callable RPC method, then wire up routing and the wrangler configuration.High-intent search queries and answers about installing and using this skill.
Extend the Agent class from the agents package, define typed state with initialState, and update it via this.setState which persists to SQLite and broadcasts to clients. Register a Durable Object binding and a new_sqlite_classes migration in wrangler.jsonc, then route requests with routeAgentRequest.
Extend AIChatAgent from @cloudflare/ai-chat and implement onChatMessage using streamText from the AI SDK, passing abortSignal and onFinish. On the client, combine useAgent with useAgentChat from @cloudflare/ai-chat/react for messages, input handling, and resumable streaming.
Yes, agents include a multi-server MCP client via this.addMcpServer, supporting OAuth flows and Streamable HTTP, SSE, or RPC transports. You can also build your own MCP server by extending McpAgent and serving it with MyMCP.serve.
Enabling experimentalDecorators in tsconfig conflicts with the decorators used by the Agents SDK and breaks @callable RPC methods. Extend the agents/tsconfig configuration instead, which sets the correct compiler options.
Use the built-in queue() for background tasks under 30 seconds with sequential FIFO processing. Use AgentWorkflow for long-running multi-step tasks, automatic retries, and human-in-the-loop approval flows that must survive failures.
biwakonbuClarify Wrangler CLI specifications and usage for Cloudflare Workers development.
greyhaven-aiImplement Cloudflare Workers observability with wrangler tail and health checks.
ecnepsyroc-botBuild stateful AI agents with durable state, scheduling, RPC, and streaming on Cloudflare Workers.
bohdanbirdieBuild stateful real-time AI agents on Cloudflare with the Agents SDK.