Dagu

Local-first workflow engine.

Declarative, file-based, self-contained, and air-gapped ready. One binary that scales from laptop to distributed cluster.

Get Started View Examples

Try It Live

Explore without installing: Live Demo

Credentials: demouser / demouser

Why Dagu?

Single binary - No database, message broker, or external services. Architecture
Declarative YAML - Define workflows without code. YAML Reference
Composable - Nest sub-workflows with parameters. Control Flow
Distributed - Route tasks to workers via labels. Distributed Execution
AI Agent - Built-in LLM-powered assistant with tools, memory, and configurable personalities. AI Agent
Workflow Operator - Persistent AI operator for Slack and Telegram. Monitor runs, debug failures, recover incidents, and continue follow-up in context. Workflow Operator
Production-ready - Retries, hooks, metrics, RBAC. Error Handling

Quick Start

Install

bash

curl -fsSL https://raw.githubusercontent.com/dagu-org/dagu/main/scripts/installer.sh | bash

powershell

irm https://raw.githubusercontent.com/dagu-org/dagu/main/scripts/installer.ps1 | iex

cmd

curl -fsSL https://raw.githubusercontent.com/dagu-org/dagu/main/scripts/installer.cmd -o installer.cmd && .\installer.cmd && del installer.cmd

bash

docker run --rm -v ~/.dagu:/var/lib/dagu -p 8080:8080 ghcr.io/dagu-org/dagu:latest dagu start-all

bash

brew install dagu

bash

npm install -g --ignore-scripts=false @dagu-org/dagu

The script installers open a guided wizard that can install Dagu, add it to your PATH, set up a background service, create the first admin, and offer Dagu AI skill installation. Homebrew, npm, Docker, and manual downloads remain available, but they do not include the guided setup flow. See the Installation Guide for details.

Create a Workflow

bash

cat > hello.yaml << 'EOF'
steps:
  - command: echo "Hello from Dagu!"
  - command: echo "Step 2"
EOF

Run

bash

dagu start hello.yaml

Start Web UI

bash

dagu start-all

Visit http://localhost:8080

Key Capabilities

Capability	Description
Nested Workflows	Reusable sub-DAGs with full execution lineage tracking
Distributed Execution	Label-based worker routing with automatic service discovery
Error Handling	Exponential backoff retries, lifecycle hooks, continue-on-failure
Step Types	Shell, Docker, SSH, HTTP, JQ, Mail, and more
Observability	Live logs, Gantt charts, Prometheus metrics, OpenTelemetry
AI Agent	Built-in LLM assistant with tool calling, persistent memory, and souls
Workflow Operator	Persistent AI operator for Slack and Telegram to manage workflows and incident follow-up
Security	Built-in RBAC (Pro) with admin, manager, operator, and viewer roles

Examples

CLI Orchestration

yaml

schedule: "0 2 * * *"
type: graph

steps:
  - id: build
    command: make build

  - id: test
    command: make test
    depends: build
    retry_policy:
      limit: 3
      interval_sec: 10

  - id: deploy
    type: ssh
    config:
      host: prod-server
    command: ./deploy.sh
    depends: test

handler_on:
  success:
    command: notify.sh "Deployment succeeded"
  failure:
    command: alert.sh "Deployment failed"

AI Agent Workflow

yaml

type: graph
steps:
  - id: analyze
    type: agent
    messages:
      - role: user
        content: "Review error logs and suggest fixes"
    output: ANALYSIS
    approval:
      prompt: "Review AI analysis before applying"

  - id: apply
    command: ./apply-fix.sh "${ANALYSIS}"
    depends: [analyze]

See Examples for more patterns.

Use Cases

CLI Orchestration - Chain shell scripts, Docker containers, and remote commands into reliable workflows
AI-Agent Workflows - LLM-powered agents with tool calling, approval gates, and memory. Manage workflows through Workflow Operator in Slack or Telegram
Deployment Automation - Multi-environment rollouts with approval gates
Scheduled Operations - Cron-based maintenance, backups, and reporting
Legacy Migration - Wrap existing scripts without rewriting them

Quick Links: Overview | CLI | Web UI | API | Architecture