workers-ai

Configure Cloudflare Workers AI bindings, streaming responses, and gateway routing.

Updated Mar 28, 2026
One-click install
npx skills add https://github.com/cffrank/paperclip-skills-agents --skill workers-ai-cffrank
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: workers-ai
Source: https://github.com/cffrank/paperclip-skills-agents/tree/main/skills/workers-ai
Command: npx skills add https://github.com/cffrank/paperclip-skills-agents --skill workers-ai-cffrank

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cloudflare Workers AI runtime patterns enable consistent bindings, streaming responses, and AI Gateway routing for edge AI workloads, reducing custom setup.

Core Features & Use Cases

  • Cloudflare-specific AI runtime patterns including binding usage, streaming responses, and model routing
  • AI Gateway setup, model catalog access, streaming interactions, and cost-aware routing
  • Use cases include configuring wrangler AI bindings, streaming chat responses, routing inference through AI Gateway, and production-ready model management

Quick Start

Create a minimal wrangler project and verify the env.AI.run integration with a sample model to validate the runtime patterns.

Frequently Asked Questions about workers-ai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure Cloudflare Workers AI bindings for edge inference?

Configuring Cloudflare Workers AI bindings requires setting up runtime patterns in a minimal wrangler project and verifying the env.AI.run integration with a sample model to validate binding access for edge inference.

What is the best way to stream AI chat responses in Cloudflare Workers?

The best way to stream AI chat responses in Cloudflare Workers is by applying specific runtime patterns that support robust streaming interactions, reducing custom setup for production-ready edge AI workloads.

Can I route inference requests through the Cloudflare AI Gateway?

Yes, you can route inference requests through the Cloudflare AI Gateway by applying its setup patterns, which enable cost-aware routing and model management across multiple providers for production usage.

Does this approach support model routing across multiple providers in Workers?

Yes, Cloudflare Workers AI runtime patterns support model routing across multiple providers by applying consistent bindings and accessing the model catalog for production-ready inference management.

Why is setting up AI workloads in Cloudflare Workers difficult without runtime patterns?

Setting up AI workloads in Cloudflare Workers is difficult without runtime patterns because production usage requires manually configuring bindings, streaming responses, and AI Gateway routing, which consistent runtime patterns reduce.