Cloudflare Agent Router — DevOps skill for Claude Code
A monorepo of AI agent router with Cloudflare Worker, Cloudflare Container, and Litellm.
How to install Cloudflare Agent Router
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open memorysaver/cloudflare-agent-router and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Cloudflare Agent Router does
A monorepo of AI agent router with Cloudflare Worker, Cloudflare Container, and Litellm.
Alternatives in DevOps
- Claude Code Router — Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the m 30.1k ★
- Cloudflare Deploy — Deploy apps to Cloudflare using Workers, Pages, and platform services 14.6k ★
- Agents Starter — A starter kit for building ai agents on Cloudflare 1.3k ★
README
Cloudflare Agent Router
Cloudflare Agent Router — a comprehensive AI agent router monorepo built on Cloudflare Workers, Containers, AI Gateway, and LiteLLM. Provides a complete solution for hosting LLM routers that support agent endpoints like Claude Code and other AI development tools.
Quick Start
You can bootstrap a new monorepo using this template by running:
npm create workers-monorepo@latest
Why a Monorepo?
Managing multiple related services (like Cloudflare Workers) in separate repositories can become complex. A monorepo approach offers several advantages:
- Simplified dependency management -
pnpm workspacesallow you to manage dependencies across all your workers and shared packages from a single place. The toolsyncpack(configured via.syncpackrc.cjs) help keep versions consistent. - Code sharing and reuse - Easily create and share common logic, types, and utilities between workers by placing them in the
packages/directory. Changes to shared code are immediately available to all consumers. - Atomic commits - Changes affecting multiple workers or shared libraries can be committed together, making the history easier to understand and reducing the risk of inconsistencies.
- Consistent tooling - Apply the same build, test, linting, and formatting configurations (e.g., via Turborepo in
turbo.jsonand shared configs inpackages/) across all projects, ensuring consistent tooling and code quality across Workers. - Streamlined CI/CD - A single pipeline (like the ones in
.github/workflows/) can build, test, and deploy all Workers, simplifying the release process. - Easier refactoring - Refactoring code that spans multiple workers or shared packages is significantly easier within a single repository.
Prerequisites
- Node.js v22 or later
- pnpm v10 or later
Getting Started
**Install Dependencies:**
just install
# or
pnpm install
**Run Development Server:**
just dev
# or
p
Related Skills
Sg Cars Trends Backend
by sgcarstrends - Provides comprehensive structure for TypeScript monorepo projects with detailed commands for
Claude Overlay
Manage project-level Claude Code configuration for custom model providers (Databricks, Bedrock, OpenRouter, Li
Workers MCP
Talk to a Cloudflare Worker from Claude Desktop!
GPT Telegram Worker
A multi-model AI Telegram bot powered by Cloudflare Workers, supporting various APIs including OpenAI, Claude,
Claude Code Nexus
Seamlessly forward Claude Code requests to any OpenAI-compatible API service with smart model mapping, streami
AI Worker Proxy
OpenAI-compatible AI proxy: Anthropic Claude, Google Gemini, GPT-5, Cloudflare AI. Free hosting, automatic fai
Related Agents
Docker Deploy
Use to build and ship container images: multi-stage builds, transitive monorepo dependencies, digest pinning,
Router Haiku
Worker subagent dispatched by the auto-model-router for trivial tasks — reads, lists, lookups, quick edits, cl
Standard Worker High
Default execution tier — most feature work, bug fixes, and moderate multi-file refactors that follow establish