dagu
Self-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler.
- 4.4k stars
- 383 forks
- 126 open issues
- Language: Go
- License: GPL-3.0
- updated
Install
git clone https://github.com/dagucloud/dagu{
"mcpServers": {
"dagu": {
"command": "dagu"
}
}
}{
"mcpServers": {
"dagu": {
"command": "dagu"
}
}
}- Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
- Replace any <placeholder> values with your API keys or paths.
- Restart Claude. The MCP server and its tools appear automatically.
Install the binary first: go install github.com/dagucloud/dagu@latest (make sure it ends up on your PATH).
Editor's note
Dagu is a self-contained, file-backed workflow orchestration engine written in Go that lets teams define directed acyclic graphs (DAGs) in declarative YAML and run them via a built-in Web UI without requiring a database like PostgreSQL or a message broker. Steps can execute shell commands, Docker containers, Kubernetes Jobs, SSH remote commands, and AI agent harnesses, all managed through a single binary that installs on Linux, macOS, or Windows. It connects to Claude and other AI agents through a built-in MCP server, allowing agents to create, trigger, monitor, and manage workflows programmatically. The Web UI provides a kanban-style cockpit view, per-step logs, retry controls, and human-in-the-loop approval steps. A standout detail is that Dagu stores all state in local files rather than an external DBMS, making it practical for edge deployments, private infrastructure, and small teams who want Airflow-style DAG orchestration without the six-plus service overhead traditional orchestrators require. DevOps engineers, data engineers, and support teams managing cron jobs or ETL pipelines benefit most.
MCP Servers overview
What people ask about dagu
What is dagucloud/dagu?
dagucloud/dagu is mcp servers for the Claude AI ecosystem. Self-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler. It has 4.4k GitHub stars and its last recorded update is dated 2026-10-23.
How do I install dagu?
You can install dagu by cloning the repository (https://github.com/dagucloud/dagu) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is dagucloud/dagu safe to use?
Our security agent has analyzed dagucloud/dagu and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains dagucloud/dagu?
dagucloud/dagu is maintained by dagucloud. The last recorded GitHub activity is dated 2026-10-23, with 126 open issues.
Are there alternatives to dagu?
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.