trigger.dev: a durable workflow engine for building and deploying long-running AI agents in TypeScript

What it solves

Trigger.dev is designed to solve the limitations of serverless platforms (like AWS Lambda or Vercel) when building AI agents and complex workflows. It eliminates execution timeouts, provides durable task execution with automatic retries, and manages the infrastructure scaling required for resource-heavy AI tasks.

How it works

Developers write background tasks directly in their TypeScript codebase using an SDK. These tasks are deployed to the Trigger.dev platform (cloud or self-hosted), which handles the orchestration, queuing, and scaling. The platform uses a checkpointing system to ensure tasks are durable and can resume from where they left off, and supports "waitpoints" for human-in-the-loop interactions.

Who it’s for

TypeScript developers building AI agents, long-running background jobs, and automated workflows that require high reliability, observability, and the ability to integrate with various LLMs and frameworks.

Highlights

• No Timeouts: Execute long-running tasks without the constraints of traditional serverless functions.
• Human-in-the-Loop: Programmatically pause tasks for human approval or feedback via waitpoints.
• Durable Execution: Built-in checkpointing, automatic retries, and idempotency to ensure tasks complete successfully.
• Runtime Freedom: Ability to customize build extensions to run system packages like Python scripts, FFmpeg, or browsers.
• Full Observability: Comprehensive logging, tracing, and real-time updates for every task run.
• Real-time Streaming: Support for streaming AI responses directly to the frontend using React hooks.