The workflow engine that doesn’t turn into an SRE project.

Dagu replaces workflow platform sprawl with a self-contained engine that is easier to run, cheaper to own, and simpler to scale.

View Examples
Try Live Demo
Login withdemouser / demouser
dagu server --port 8080
Install dagu command
$curl -fsSL https://raw.githubusercontent.com/dagu-org/dagu/main/scripts/installer.sh | bash

Guided installer: adds Dagu to your PATH, sets up a background service, creates the first admin, and can install the Dagu AI skill.

Zero Intrusion

No SDK required. Your code stays untouched.

Self-contained

Single binary, no external dependencies

Language agnostic

Run any script, any language

Air-Gapped Ready

Runs fully offline. No external services needed.

workflow.yaml
# CLI + AI agent workflow
name: "log-analyzer"
schedule: "0 0 * * *"

steps:
- name: "collect-logs"
command: "grep ERROR /var/log/app/*.log"
output: ERRORS

- name: "ai-analyze"
type: agent
messages:
- role: user
content: "Analyze: $${ERRORS}"
Cockpit demo

Built for real workflows

From shell scripts to AI agents, automate it all in simple YAML.

Health Check
SSH Backup
Notify

CLI Orchestration

Chain shell commands, Docker containers, SSH sessions, and HTTP calls into reliable automated workflows.

  • 1Orchestrate any CLI command without code changes
  • 2Run containers, SSH into servers, make HTTP calls
  • 3Parallel execution with dependency management
  • 4Automatic retries with exponential backoff
workflow.yaml
steps:
  - name: health-check
    command: curl -sf http://app:8080/health

  - name: backup
    type: ssh
    config:
      host: db-server
      user: admin
    command: pg_dump mydb > /backups/daily.sql

  - name: notify
    type: http
    config:
      url: "https://hooks.slack.com/..."
      method: POST
    body: '{"text": "Backup complete"}'

Workflow Operator for Slack & Telegram

Persistent AI operator for Slack and Telegram.Debug failures, approve actions, and recover incidents without leaving the conversation.

DaguDagu
Message...

How Dagu Compares

AI agent that creates and manages deterministic workflows.Not the other way around.

Deterministic execution
DaguDaguOpenClawOpenClawAirflowAirflow
Built-in AI agent
DaguDaguOpenClawOpenClawAirflowAirflow
Create workflows via chat
DaguDaguOpenClawOpenClawAirflowAirflow
Debug failed runs via chat
DaguDaguOpenClawOpenClawAirflowAirflow
Scheduled jobs
DaguDaguOpenClawOpenClawAirflowAirflow
Token-efficient agentic workflow
DaguDaguOpenClawOpenClawN/AAirflowAirflow
Built-in memory
DaguDaguOpenClawOpenClawAirflowAirflow
Built-in documentation & runbook
DaguDaguOpenClawOpenClawAirflowAirflow
Run coding agent
DaguDaguOpenClawOpenClawAirflowAirflow
Minimum infrastructure cost
lowDaguDagulowOpenClawOpenClaw$200+/moAirflowAirflow

Automate CLI commands, AI agents, and everything in between

Everything you need in a single binary. No external dependencies required.

Quickstart Guide

Install Dagu with the guided wizard, then continue in the full installation guide or quickstart docs.

1

Install dagu command

The script installers are the recommended path. Homebrew, npm, and Docker remain available for binary-only or container installs.

Mac/Linux Terminal
$curl -fsSL https://raw.githubusercontent.com/dagu-org/dagu/main/scripts/installer.sh | bash
✓ Guided installer ready
2

Next steps

The guided installer can finish the first-run setup for you.

# What the installer can do
Add Dagu to your PATH
Set up a background service
Create and verify the first admin
Offer Dagu AI skill installation
# If you use an AI coding tool, run this after installing Dagu
$dagu ai install --yes
# Fallback via the shared skills CLI
$npx skills add https://github.com/dagu-org/dagu --skill dagu
Open Source Community

Join our community!

Built by the community, for the community.