Agent skill · AI & Agents

cloudflare-agents

Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 23 documented errors. Use when: building WebSocket agents, RAG with Vectorize, MCP servers, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors, WebSocket payload limits.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill cloudflare-agents-brendadeeznuts1111-tier-1380-omega --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 56 KB
Bundled scripts: none
Path: skills/agent/cloudflare-agents-brendadeeznuts1111-tier-1380-omega/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 23 documented errors.

How it works

Describes infrastructure-level features: WebSocket connections, Durable Objects wrappers for globally unique agent instances, built-in SQLite state persistence up to 1GB per agent, and scheduling capabilities via this.schedule() with cron or delays. Supports multi-agent coordination via routeAgentRequest() and lifecycle methods like onStart/onConnect/onMessage/onClose. Offers client libraries such as useAgent, AgentClient, and agentFetch. Emphasizes that it does NOT provide AI inference or streaming parsing; you bring your own AI SDK or provider.

When to use it

Use when you need WebSocket bidirectional communication, durable stateful agents, multi-agent coordination, scheduling, or human-in-the-loop workflows, especially for long-running agents or MCP servers.

What it can touch

  • WebSocket connections
  • Durable Objects bindings
  • SQLite state storage (up to 1GB per agent)
  • Scheduling with this.schedule()
  • Multi-agent routing via routeAgentRequest()
  • Client libraries: useAgent, AgentClient, agentFetch

Caveats

  • Not an AI inference provider; requires integrating an AI SDK/provider separately
  • Requires Durable Objects setup and potential migrations (e.g., new_sqlite_classes) as described in examples
  • Complexity and code footprint are higher compared to using AI SDK alone
From the SKILL.md

# Cloudflare Agents SDK **Status**: Production Ready ✅ **Last Updated**: 2026-01-09 **Dependencies**: cloudflare-worker-base (recommended) **Latest Versions**: agents@0.3.3, @modelcontextprotocol/sdk@latest **Production Tested**: Cloudflare's own MCP servers (https://github.com/cloudflare/mcp-server-cloudflare) **Recent Updates (2025-2026)**: - **Jan 2026**: Agents SDK v0.3.6 with callable methods fix, protocol version support updates - **Nov 2025**: Agents SDK v0.2.24+ with **resumable streaming** (streams persist across disconnects, page refreshes, and sync across tabs/devices), MCP client improvements, schedule fixes - **Sept 2025**: AI SDK v5 compatibility, automatic message migration - **Aug 2025**: MCP Elicitation support, http-streamable transport, task queues, email integration - **April 2025**: MCP support (MCPAgent class), `import { context }` from agents - **March 2025**: Package rename (agents-sdk → agents) ### Resumable Streaming (agents@0.2.24+) AIChatAgent now supports **resumable streaming**, enabling clients to reconnect and continue receiving streamed responses without data loss. This solves critical real-world scenarios: - Long-running AI responses that exceed co

What's inside
Steps it walks through
  1. Resumable Streaming (agents@0.2.24+)
  2. What is Cloudflare Agents?
  3. Do You Need Agents SDK?
  4. Use JUST Vercel AI SDK (Simpler) When:
  5. Use Agents SDK When You Need:
  6. Key Understanding: What Agents SDK IS vs IS NOT
  7. Decision Flowchart
  8. Architecture Comparison
  9. Still Not Sure?
  10. Quick Start (10 Minutes)
  11. 1. Scaffold Project with Template
  12. 2. Or Add to Existing Worker
  13. 3. Configure Durable Objects Binding
  14. 4. Deploy
Ships with 1 file
  • metadata.json
Commands it runs
npm create cloudflare@latest my-agent -- \
cd my-existing-worker
npm install agents
npx wrangler@latest deploy
npm install @modelcontextprotocol/sdk agents
Run MCP inspector
npx @modelcontextprotocol/inspector@latest
Connect to: http://localhost:8788/mcp
More from claude-skill-registry
All skills →
About this skill
What does the cloudflare-agents skill do?

Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 23 documented errors. Use when: building WebSocket agents, RAG with Vectorize, MCP servers, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors, WebSocket payload limits.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill cloudflare-agents-brendadeeznuts1111-tier-1380-omega --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going