Documentation
flowwork is a Postgres-backed, durable, agent-native workflow engine that ships as one static binary. You author workflows in a flat JavaScript DSL and drive them with flowctl — steps run, and when a run needs the outside world (a form, a webhook, an API call, an AI agent) it parks in Postgres and resumes when the event arrives.
It's built to blend three paths in a single workflow: the deterministic (steps, branches, and retries that run the same way every time), the generative (an LLM call as just another step), and the agentic (hand a step to a general agent like Claude Code or Codex to get the work done). Author once, then mix hard logic, model inference, and agent judgement exactly where each fits.
Start here
Install flowwork, start the engine, and run your first workflow in five minutes.
Build a human-in-the-loop approval from scratch — and watch a run park and resume.
Every builder, option, and condition on one page. The 'I just need the syntax' reference.
Browse by topic
The JavaScript DSL: steps, control flow, forms, triggers, retries, and outcomes.
Call external services — HTTP, LLMs, and any MCP server — from a workflow step.
The agent() step and bidirectional human-in-the-loop over Claude Code channels.
Install, configure, deploy, and understand licensing, machines, and limits.
flowctl --help lists every command.