Build stateful AI agents on Cloudflare Workers using the Agents SDK.
npx skills add https://github.com/mintuz/.dotfiles --skill agents-sdk-mintuz
Please help me install this Agent Skill. Skill: agents-sdk Source: https://github.com/mintuz/.dotfiles/tree/main/agents/.agents/skills/agents-sdk Command: npx skills add https://github.com/mintuz/.dotfiles --skill agents-sdk-mintuz
@callable RPC methods, scheduling, and automatic client sync via React hooks like useAgent. - Chat & Streaming: Build streaming chat agents with AIChatAgent, resumable streams, tool calling, and human-in-the-loop approval flows. - Background Processing: Coordinate durable Workflows, built-in FIFO queues, retries with backoff, and durable execution fibers that survive Durable Object eviction. - Use Case: Build a customer support chat agent that persists conversation history, schedules follow-up reminders, connects to MCP servers for external tools, and streams responses to a React frontend. ## Quick Start Ask the AI to create a Cloudflare Worker agent class with persistent state and a callable RPC method using the Agents SDK.High-intent search queries and answers about installing and using this skill.
Extend the Agent class from the agents package, define an initialState, and register a Durable Object binding with a new_sqlite_classes migration in wrangler.jsonc. Route requests with routeAgentRequest and expose methods to clients using the @callable decorator.
Extend AIChatAgent from @cloudflare/ai-chat and implement onChatMessage using streamText from the AI SDK. Pass abortSignal and onFinish for proper cleanup and message persistence; streams resume automatically on client reconnect.
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 MCP servers by extending McpAgent and serving them with MyMCP.serve.
Enabling experimentalDecorators in tsconfig conflicts with the decorator implementation used by @callable, breaking RPC method exposure. Extend the agents/tsconfig base 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.
vedangBuild stateful AI agents on Cloudflare Workers using the Agents SDK.
aashahinBuild stateful AI agents on Cloudflare Workers using the Agents SDK.
AgentiveCityConfigure structured logging, tracing, and Sentry integration for Cloudflare Workers.
joelhooksBuild Cloudflare Durable Objects for per-agent state, WebSockets, and hibernation.