trigger.dev

trigger.dev

Background job platform used with Claude Code to host agents and workflows in production. Provides scheduled runs, automatic retries, queuing, orchestration, and a clean UI for watching live executions. TypeScript-based tasks deploy from a GitHub repo auto-synced via push. Supports MCP server integration and environment-variable secrets stored in the trigger.dev UI.

Key facts

  • TypeScript task files live under src/trigger/ in the project
  • Dev environment connects to a running local dev server; prod deploys from GitHub auto-sync
  • Supports cron schedules, automatic retries, queues, and multi-task orchestration
  • Runs can span multiple tasks with deduplication and idempotency
  • Official trigger.dev MCP server lets Claude Code deploy and test jobs directly
  • Environment variables (API keys) must be added in both dev and prod via the trigger.dev UI
  • In Nate's 2026 deployment comparison, trigger.dev is positioned as a cloud workflow/runtime layer: excellent for scheduled, durable, observable TypeScript workflows, and agentic only when the developer explicitly embeds an agent SDK or model call [src-086].

Source references

  • [src-004] Nate Herk cluster — Nate Herk — Claude Code cluster (21 videos)

– Videos referenced: UGIZnh6HNLc, 27Y44JYXZJ8

  • [src-086] Nate Herk — "I Tested 3 Ways to Deploy Claude Agents (Here's When to Use Each)" (2026-05-15)

Robin Cartier perspective

This page is part of Robin Cartier's working AI knowledge graph: a practical research layer for production AI, recommendation systems, experimentation, GEO, and agentic web readiness.

The useful next step is to connect this concept back to applied product leadership and operating models.

Recommended next

Keep reading from this thread

From 491 indexed pages and articles.

  1. Wiki concept Agent Deployment Modes The practical choices for where an AI agent or automation runs and whether the live reasoning loop is still Related by dev
  2. Wiki concept Claude Managed Agents Anthropic-hosted agent platform launched April 2026 that lets users define an agent (name, system prompt, model, tools, MCP connections, skills) and deploy it Related by deploy
  3. Insight AI Beyond POCs How enterprise AI moves beyond proofs of concept through ownership, governance, measurement, adoption, and production operating models Readers have engaged with this next