Works with the AI tools you already use
Elite Cloudflare Agent
Build stateful AI agents with persistent memory, SQLite, and cron scheduling on Cloudflare's global edge network.
Secure checkout via Stripe
See it in action
You say
Create a stateful MCP agent that monitors a weather API every hour and stores the history in a local SQLite table.
Your agent does
Successfully deployed WeatherMonitor agent. Features:
- Cron: Hourly 'fetchWeather' task
- Storage: 'weather_history' SQLite table
- RPC: '@callable getAverageTemp()'
- MCP: 'current-weather' tool for Claude Status: Live at https://weather-monitor.workers.dev
What you get
About this skill
Stateful AI Agents on the Edge
The Cloudflare Agents SDK is a powerful TypeScript framework designed for developers building persistent, stateful AI agents on Cloudflare's global network. By leveraging Durable Objects, each agent functions as an addressable compute instance with its own private SQLite storage, WebSocket capabilities, and automated lifecycle management.
What it does
- Persistent Identity: Maintains state and memory across sessions, months, or years, unlike standard serverless functions.
- Native SQLite: Built-in synchronous SQL access for high-performance data management within the agent.
- Advanced Scheduling: Robust task queue and cron system for reminders, daily digests, and delayed actions.
- Real-time RPC: Exposes typed methods via WebSockets, enabling instant communication with React frontends or other agents.
- MCP Server Integration: Transform agents into Model Context Protocol (MCP) servers to power tools for Claude Code, Cursor, and IDEs.
Why use this skill?
Building stateful agents usually requires managing complex database syncs, message queues, and WebSocket servers. This skill abstracts that infrastructure away. It is better than simple prompting because it provides the "body" for the AI—giving it a reliable memory, the ability to act on a schedule, and a secure way to interface with external APIs and local state. The output is a production-ready serverless architecture capable of scaling to millions of individual agents with zero idle costs.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 1 month ago
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Also available in a bundle
Frequently Asked Questions
Popular in AI Agents & LLM Ops
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
Open Browser Use
Automate real Chrome profiles with a professional CLI, SDK, and MCP-ready automation stack for AI agents.
Making Complex Systems Agent-Readable with Grok (v1.0.1)
Turn complex system documentation into structured, agent-accessible knowledge bases optimized for MCP and AI tools.
Getting Started with OpenCode and Agensi (v1.1)
Bridge OpenCode to the Agensi marketplace to discover and install AI agent skills via MCP.