Build stateful AI agents on Cloudflare Workers using the Agents SDK.
npx skills add https://github.com/vedang/dotagents --skill agents-sdk-vedang
Please help me install this Agent Skill. Skill: agents-sdk Source: https://github.com/vedang/dotagents/tree/main/specific_skills/agents-sdk Command: npx skills add https://github.com/vedang/dotagents --skill agents-sdk-vedang
@callable RPC methods, and automatic client state sync via React hooks like useAgent and useAgentChat. - Durable Background Work: Run scheduled tasks, cron jobs, FIFO queues with retries, durable fibers, and multi-step Workflows with human-in-the-loop approvals. - Chat, MCP, and Integrations: Build streaming chat agents with AIChatAgent, connect to or host MCP servers, handle email, webhooks, push notifications, voice, and browser automation. - Use Case: Build a customer support chat agent that persists conversation history, schedules follow-up checks, calls MCP tools, and resumes streams automatically when users reconnect. ## Quick Start Ask the agent to create a Cloudflare Workers agent using the Agents SDK with a Counter class, state management, and a callable increment method.High-intent search queries and answers about installing and using this skill.
Install the agents package, extend the Agent class with typed state, and route requests with routeAgentRequest. Configure a Durable Object binding and a new_sqlite_classes migration in wrangler.jsonc for each agent class.
Use this.schedule() with a delay in seconds, a Date, or a cron expression, or this.scheduleEvery() for fixed intervals. The handler method receives the payload and schedule object, and cron schedules auto-reschedule.
AIChatAgent gives full control over the streamText loop inside onChatMessage, while Think handles the loop, tool execution, and persistence automatically via getModel() and getSystemPrompt(). Think requires the experimental compatibility flag.
Yes, agents include a multi-server MCP client via this.addMcpServer() with OAuth support, and this.mcp.getAITools() exposes MCP tools to the LLM. You can also build MCP servers using the McpAgent class.
Enabling experimentalDecorators in tsconfig conflicts with the decorators used by the Agents SDK and breaks @callable methods. Extend the agents/tsconfig base configuration instead to get correct compiler settings.
Use the built-in queue() for background tasks under 30 seconds and Workflows for long-running multi-step tasks needing automatic retries, durable state, or human approval flows via step.waitForEvent.
sota411Build stateful AI agents on Cloudflare Workers using the Agents SDK.
aashahinBuild stateful AI agents on Cloudflare Workers using the Agents SDK.
openaiBuilds and deploys remote MCP servers on Cloudflare Workers with OAuth authentication.
CommandCodeAICreate and deploy stateful Cloudflare AI agents with WebSocket communication and tool integration.