/* Tooltip style on the code block */
div[class="absolute top-11 left-1/2 transform -translate-x-1/2 -translate-y-1/2 hidden group-hover:block text-white rounded-lg px-1.5 py-0.5 text-xs bg-primary-dark"] {
  color:#1A1B1F;
  border-radius: 0.25rem;
}

/* Link anchor active state - icon container */
div[class="mr-4 rounded-md p-1"] {
  border-radius: 0.25rem;
  border: 1px solid #464748;
}

/* Link anchor default state - icon container */
div[class="mr-4 rounded-md p-1 zinc-box group-hover:brightness-100 group-hover:ring-0 ring-1 ring-gray-950/5 dark:ring-gray-700/40"] {
  border-radius: 0.25rem;
  border: 1px solid transparent;
}

Overview

Real world AI agent example tasks using Trigger.dev

AI agents overview

Trigger.dev is an open source background jobs framework that lets you write reliable workflows in plain async code. Run long-running AI tasks, handle complex background jobs, and build AI agents with built-in queuing, automatic retries, and real-time monitoring. No timeouts, elastic scaling, and zero infrastructure management required.

Trigger.dev

Find all the resources and guides you need to get started

Introduction

Welcome to the Trigger.dev docs

How to get started in 3 minutes using the CLI and SDK.

Quick start

Go from zero to a working task in your Next.js app in 10 minutes.

Video walkthrough

Understand how Trigger.dev works and how it can help you.

How it works

There are some hard and soft limits that you might hit.

Limits

What's new in v4, how to upgrade, and breaking changes.

Upgrading to v4

Tasks need to be triggered in order to run.

Triggering

Understanding the lifecycle of task run execution in Trigger.dev

Runs

How to authenticate with Trigger.dev so you can trigger tasks.

API keys

Tasks are the core of Trigger.dev. They are long-running processes that are triggered by events.

Writing tasks: Overview

How to use the built-in logging and tracing system.

Logging and tracing

How to deal with errors and write reliable tasks.

Errors & Retrying

Configure what you want to happen when there is more than one run at a time.

Concurrency & Queues

We use atomic versioning to ensure that started tasks are not affected by changes to the task code.

Versioning

Configure the number of vCPUs and GBs of RAM you want the task to use.

Machines

An API call or operation is “idempotent” if it has the same result when called more than once.

Idempotency

Set a maximum duration for a task to run.

Max duration

Tags allow you to easily filter runs in the dashboard and when using the SDK.

Metadata

Run metadata

Get compute duration and cost from inside a run, or for a specific block of code.

Usage

Context

This file is used to configure your project and how it's built.

trigger.config.ts

The trigger.config.ts file

The `trigger.dev dev` command is used to run your tasks locally.

CLI dev command

Learn how to deploy your tasks to Trigger.dev.

Deployment

Any environment variables used in your tasks need to be added so the deployed code will run successfully.

Environment Variables

You can easily deploy your tasks with GitHub actions.

GitHub Actions

Use atomic deploys to coordinate changes to your tasks and your application.

Atomic deploys

Using the Trigger.dev SDK from your frontend application.

Overview & Auth

Overview & Authentication

Realtime overview

Stream data in realtime from inside your tasks

Streams

Realtime streams

Subscribes to all changes to a run in a React component.

React hooks

Realtime React hooks

subscribeToRun

runs.subscribeToRun

Subscribes to all changes to runs with a specific tag.

subscribeToRunsWithTag

runs.subscribeToRunsWithTag

Subscribes to all changes for runs in a batch.

subscribeToBatch

runs.subscribeToBatch

The Trigger.dev CLI has a number of options and commands to help you develop locally, self host, and deploy your tasks.

You can use the dashboard to run a test of your tasks.

Run tests

Get alerted when runs or deployments fail, or when deployments succeed.

Alerts

A replay is a copy of a run with the same payload but against the latest version in that environment. This is useful if something went wrong and you want to try again with the latest version of your code.

Replaying

Perform actions like replay and cancel on multiple runs at once.

Bulk actions

Some common problems you might experience and their solutions

Common problems

Debugging in VS Code

When we release fixes and new features we recommend you upgrade your Trigger.dev packages.

Upgrading packages

How to upgrade the Trigger.dev packages

Uptime Status

GitHub Issues

Request a feature

You can self-host Trigger.dev on your own infrastructure.

Self-hosting

You can contribute to Trigger.dev in many ways.

Contributing

GitHub repo

Changelog

Roadmap

Discord Community

Slack support

Email us

Authenticating with the Trigger.dev management API

Authentication

Handling errors and retries with the Trigger.dev management API

Errors and retries

Using auto-pagination with the Trigger.dev management API

Auto-pagination

Advanced usage of the Trigger.dev management API

Advanced usage

Trigger

Batch trigger tasks with up to 500 payloads.

Batch trigger

List runs in a specific environment. You can filter the runs by status, created at, task identifier, version, and more.

List runs

Retrieve information about a run, including its status, payload, output, and attempts. If you authenticate with a Public API key, we will omit the payload and output fields for security reasons.


Retrieve run

Creates a new run with the same payload and options as the original run.

Replay run

Cancels an in-progress run. If the run is already completed, this will have no effect.

Cancel run

Updates a delayed run with a new delay. Only valid when the run is in the DELAYED state.

Reschedule run

Update metadata

List all schedules. You can also paginate the results.

List Schedules

Create a new `IMPERATIVE` schedule based on the specified options.

Create Schedule

Retrieve Schedule

Update a schedule by its ID. This will only work on `IMPERATIVE` schedules that were created in the dashboard or using the imperative SDK functions like `schedules.create()`.

Update Schedule

Delete a schedule by its ID. This will only work on `IMPERATIVE` schedules that were created in the dashboard or using the imperative SDK functions like `schedules.create()`.

Delete Schedule

Deactivate a schedule by its ID. This will only work on `IMPERATIVE` schedules that were created in the dashboard or using the imperative SDK functions like `schedules.create()`.

Deactivate Schedule

Activate a schedule by its ID. This will only work on `IMPERATIVE` schedules that were created in the dashboard or using the imperative SDK functions like `schedules.create()`.

Activate Schedule

Get all supported timezones that schedule tasks support.

Get timezones

List all environment variables for a specific project and environment.

List Env Vars

Upload mulitple environment variables for a specific project and environment.

Import Env Vars

Create a new environment variable for a specific project and environment.

Create Env Var

Retrieve a specific environment variable for a specific project and environment.

Retrieve Env Var

Update a specific environment variable for a specific project and environment.

Update Env Var

Delete a specific environment variable for a specific project and environment.

Delete Env Var

A growing list of guides and examples to get the most out of Trigger.dev.

Frameworks, guides and examples

This guide will show you how to setup Trigger.dev with Bun

Bun guide

This guide will show you how to setup Trigger.dev in your existing Next.js project, test an example task, and view the run.

Next.js

Next.js setup guide

This guide will show you how to setup Trigger.dev in your existing Node.js project, test an example task, and view the run.

Node.js

Node.js setup guide

This guide will show you how to setup Trigger.dev in your existing Remix project, test an example task, and view the run.

Remix

Remix setup guide

A plugin for SvelteKit to integrate with Trigger.dev.

SvelteKit

SvelteKit setup guide

This guide shows how to add Cursor rules to a project to help you write Trigger.dev tasks faster and more accurately.

Cursor rules

Using Cursor with Trigger.dev

This guide will show you how to set up Drizzle ORM with Trigger.dev

Drizzle setup guide

This guide will show you how to set up Prisma with Trigger.dev

Prisma setup guide

This guide will show you how to trigger tasks from database changes using Sequin

Sequin database triggers

Learn how to use Trigger.dev with Python to process images from URLs and upload them to S3.

Process images

Python image processing example

Learn how to use Trigger.dev with Python to convert documents to markdown using MarkItDown.

Convert docs to markdown

Convert documents to markdown using Python and MarkItDown

Learn how to use Python, Crawl4AI and Playwright to create a headless browser web crawler with Trigger.dev.

Headless web crawler

Python headless browser web crawler example

Learn how to use Trigger.dev with Python to extract form data from PDF files.

Extract form data from PDFs

Python PDF form extractor example

This example Next.js project evaluates multiple LLM models using the Vercel AI SDK and streams updates to the frontend using Trigger.dev Realtime.

Batch LLM Evaluator

Next.js Batch LLM Evaluator

This example Next.js project uses Vercel's AI SDK and Anthropic's Claude 3.7 model to create a thinking chatbot.

Claude thinking chatbot

Claude 3.7 thinking chatbot

This example project creates audio summaries of newspaper articles using a human-in-the-loop workflow built with ReactFlow and Trigger.dev waitpoint tokens.

Introduction

Frameworks

Guides

Python guides

Example projects

Example tasks

Migration guides

Community packages

AI agents overview

Overview

Prompt chaining

Routing

Parallelization

Orchestrator

Evaluator-optimizer

Introduction

Frameworks

Guides

Python guides

Example projects

Example tasks

Migration guides

Community packages

​Overview

Prompt chaining

Routing

Parallelization

Orchestrator

Evaluator-optimizer

Overview