automation

Trigger.dev: Automate AI Workflows

Deploy AI agents with trigger.dev, a tool.
intermediate1-2 hours💵 Free + LLM API costs
16,241 stars1,444 forksTypeScriptGuide quality 8/10Updated 9/9/2026100% free · open source
What it is

Deploy and manage AI agents on your platform with triggers and workflows.

Real use case example

"A founder, Alex, wants to automate the process of welcoming new customers. She sets up a trigger in Trigger.dev that listens for new Stripe customers, adds them to her Notion database, and then sends a welcome email via Resend. With this automation, Alex saves time and ensures a seamless customer experience."

Best insideClaude DesktopCursor
When to use it
  • When you need to automate repetitive tasks using AI
  • When you want to integrate machine learning models into your workflow
  • When you need to deploy AI-powered workflows without managing infrastructure
Ready-to-paste prompt
npx trigger new my-agent --workflow 'github webhook -> send slack notification'
Heads up: Make sure you have Node.js 16 or later installed, as Trigger.dev requires it to run
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/trigger-dev && curl -fsSL https://workflowstacks.com/api/skills/trigger-dev/claude-skill -o ~/.claude/skills/trigger-dev/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Trigger.dev: Automate AI Workflows works
Codeflow
Free to inspect

Trigger.dev: Automate AI Workflows is a very large TypeScript project (~656k lines across 4188 code files, plus 700 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~656k lines · 4188 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js · Docker
Needs API keys (.env)
TypeScript 99%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    package.json
    Dependencies and the commands it exposes
  4. 4
    .env.example
    The API keys and settings you must provide
What's in each folder
rules/Prompts, skills & agent definitions11 files
apps/Sub-packages / plugins2659 files
packages/Sub-packages / plugins744 files
docs/Documentation532 files
internal-packages/Folder1778 files
hosting/Folder45 files
docker/Deployment / infrastructure25 files
scripts/Helper scripts16 files
READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
triggerdotdev
Language
TypeScript
Category
automation
Published
11/30/2022

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.