DevSource: AY Automate

API Rate Limit Watchdog

Monitors how close a workflow's API calls are running to a provider's rate limit and throttles or pauses execution before you get hard-blocked, instead of finding out from a stack of failed calls.

Have AY Automate build thisBack to directory

What this template does

Monitors how close a workflow's API calls are running to a provider's rate limit and throttles or pauses execution before you get hard-blocked, instead of finding out from a stack of failed calls. It's categorized in our directory under Dev & Agent Automation — agent coordination, CI/CD glue, and developer-tool integrations — including our own Claude Code + n8n templates.

Integrations

  • Slack
    Slack

Setup steps

  1. 1Track call counts against the known rate limit for each integrated API.
  2. 2Set a warning threshold below the hard limit (e.g. 80%).
  3. 3Throttle or pause the workflow automatically past the threshold.
  4. 4Alert the team so the underlying volume issue gets addressed.

More Dev templates

Other dev & agent automation templates in our directory.

n8n

n8n + Claude Code Agent Coordinator

A Telegram-triggered n8n workflow that routes messages to a LangChain agent (via OpenRouter) with buffered memory, custom tools, and an SSH node that runs commands against a remote Claude Code session — built to coordinate multiple agent tasks from a chat interface.

n8n

n8n Claude Code Terminal Bridge

A minimal n8n workflow that exposes a chat trigger, formats the incoming message with a Set node, and pipes it over SSH into a running Claude Code CLI session — the smallest possible bridge between a chat UI and a real terminal agent.

n8n

AI Agent Production Deployment Checklist

How we take an agent from a working laptop demo to production: scoped credentials instead of a master key, a sandboxed execution environment, eval gates before shipping a prompt change, observability on every run, and a rollback path.

Claude Code

Claude Code Skills System

How we standardize repeatable engineering work as versioned Claude Code skills, so every build starts from a proven playbook — publishing, audits, image pipelines, SEO checks, and deploy safety are all captured as skills, not one-off prompts.