dagu

What it is

Dagu is a local-first workflow engine for ops automation and AI-assisted operations. It is open source and self-hostable: a single binary with a built-in Web UI, no external database or message broker, running on Linux / Mac / Windows. Define DAGs in a declarative YAML format. It natively supports shell commands, Docker containers, Kubernetes Jobs, remote commands via SSH, external coding-agent CLIs through harness.run, and more through Dagu Actions.

Dagu turns existing scripts, runbooks, and agent-driven jobs into production workflows with scheduling, retries, approvals, and run history. It runs where your data and credentials live: on-prem, air-gapped, edge, or cloud, and scales from a single node to a distributed worker fleet.

Highlights include: single binary file installation; declarative YAML for DAGs; Web UI for managing pipelines; self-contained with no DBMS; built-in MCP support for AI agents to manage workflows; run external coding-agent CLIs via harness.run.

How it works

Dagu stores state in local files and can run in standalone or distributed configurations. Workflows are defined in YAML, with steps that may run shell commands, Docker containers, Kubernetes Jobs, SSH commands, or external coding-agent CLIs. It provides scheduling, retries, approvals, and run history, and exposes a Web UI for observability and control. Architecture supports standalone server (dagu start-all), coordinator/worker, or headless mode (DAGU_HEADLESS).

Key aspects:

• Single binary with built-in Web UI
• No external database or message broker
• YAML-defined DAGs with steps and dependencies
• Supports multiple step runtimes and actions via Dagu Actions
• MCP server for AI agents integration
• Optional distributed worker mode for scalability

Getting started

Install (Quick Start)

macOS/Linux:

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

Homebrew:

brew install dagu

npm:

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

Windows (PowerShell):

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

Docker:

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

Kubernetes (Helm):

helm repo add dagu https://dagucloud.github.io/dagu
helm repo update
helm install dagu dagu/dagu --set persistence.storageClass=<your-rwx-storage-class>

Replace <your-rwx-storage-class> with a StorageClass that supports ReadWriteMany. See charts/dagu/README.md for chart configuration.

The script installers run a guided wizard that can add Dagu to PATH, set it up as a background service, and create the initial admin account. Homebrew, npm, Docker, and Helm install without the wizard.

Run a workflow

Create hello.yaml:

steps:
  - id: hello
    run: echo "hello from Dagu"

Run the workflow:

dagu start hello.yaml

Start the server

dagu start-all --dags .

Visit http://localhost:8080

Connect AI agents through MCP

Dagu exposes a built-in MCP server from the running HTTP server. Access at:

http://localhost:8080/mcp

Use MCP to have AI agents read Dagu state, preview or apply workflow changes, and start or stop runs via CLI helpers like dagu_read, dagu_change, and dagu_execute.

What you can configure

Dagu supports parameters in workflows that render as typed input forms in the Web UI and can be referenced by steps. Example shows string and boolean parameters with a retry_policy per step.

Releases

The latest releases include v2.11.4 (2026-08-03) with added registry resolution, and v2.11.3 (2026-08-02) with practical CLI commands for managing Dagu from the terminal, such as dagu ls and dagu ps. The Helm chart release v2.11.3 (2026-08-01) publishes the packaged dagu Helm chart for the repository at https://dagucloud.github.io/dagu. Previous versions include v2.11.2 and v2.11.1 with feature and safety updates.

Traction

Stars: 3697, Forks: 297, Open issues: 57

Licensing

• Community self-host: No license key required. Self-hosted server, storage, upgrades, networking, and workers.
• Self-host licensing: Adds SSO, RBAC, audit logging, and incident SaaS integration.