AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Workflow Automation/
dagu
dagu logo

dagu

Active·★ 4.6k·GPL-3.0·Updated 2026-11-21

Dagu describes itself as a local-first control plane for existing operations automation and AI agent workflows. You define workflows in declarative YAML, run them anywhere with one static binary, compose pipelines from reusable sub-workflows and distribute tasks across workers, with a built-in web UI. The README stresses that it is local-first and self-hosted (no databases, brokers or sidecars, state in local files), language-agnostic (no need to rewrite existing scripts) and that AI agents can manage workflows through MCP or a skill.

Its example use cases include ETL and data operations, replacing opaque cron jobs and bash scripts with DAGs that have a UI, logging, retries and notifications, media conversion with ffmpeg, SSH-based server automation, GitHub-event-driven workflows on private infrastructure, Docker and Kubernetes job steps, support tooling for non-engineers, and IoT or edge jobs. On performance the README is careful: throughput depends on hardware, workflow shape, queue settings and worker capacity, and on one machine it can run thousands of runs per day when they fit. Install with the shell installer, Homebrew or PowerShell, and there is a live demo. The code is GPL-3.0 licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-15.

License
GPL-3.0
Latest release
v2.26.0 · 2026-11-07
Last commit
2026-11-15
Contributors
125
Forks
402
Open issues and PRs
199
First published
2022-04-22

Source: GitHub, npm and PyPI public APIs.

#agentic-workflow#cron#data-pipeline#devops#durable-execution#durable-workflows#human-in-the-loop#job-scheduler
$ Install
$ curl -fsSL https://raw.githubusercontent.com/dagucloud/dagu/main/scripts/installer.sh | bash
↗ Visit site★ GitHub
01

Features

01Local-first and self-hosted with a single binary
02Language-agnostic workflow definition (YAML for shell, Docker, K8s, etc.)
03Built-in Web UI for observability and debugging
04Integrated AI agent support (via MCP server, harness)
05Built-in secret management and human-in-the-loop approvals
02

Why choose it

+One static binary with no database or broker; workflows are plain YAML and run existing scripts in any language.
+Built-in web UI with run details and logs, retries and notifications, plus queues and concurrency limits.
+Can distribute tasks across workers, and AI agents can drive it through MCP or a skill.
+Honest performance guidance: it depends on hardware, workflow shape and queue settings.
03

Trade-offs

!State is stored in local files, so large or highly available setups need workers and careful design rather than a central database.
!It is licensed under GPL-3.0, which has copyleft implications for derivative or embedded use.
!The README is long (about 38,000 characters) and the live demo uses a shared public login.
04

Maintenance check

ActiveChecked: 2026-11-06
Last commit
2026-11-06
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
v2.25.8 (2026-11-05)
Open issues
169
Recent issues with at least one comment
6/24
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 31, 32, 30, 51, 33, 32, 73, 66, 92, 53, 115, 190

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #1452 [FEAT] Add webhook callback after task completion15 comments · 2025-12-06
  • #1814 let dagu connect to codex / antrophics agents sdk16 comments · 2026-03-20
  • #1181 Add file triggers to run DAGs on file events10 comments · 2025-08-10
  • #2047 Queues are not used when DAG is called as sub dag9 comments · 2026-04-28
  • #3288 Feedback: replacing workspaces with projects in v3.07 comments · 2026-10-22

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

macOS
macOS
Verified via docs
Linux
Linux
Verified via docs
Windows
Windows
Verified via docs
Docker
Docker Container
Verified via docs
Kubernetes
Kubernetes
Verified via docs
06

Quick start

1
$ curl -fsSL https://raw.githubusercontent.com/dagucloud/dagu/main/scripts/installer.sh | bash
07

Use cases

↳ETL and data operations: Turn data extraction scripts, SQL queries, dbt commands, and data-processing runbooks into observable pipelines.
↳Cron and legacy script management: Transform complex, interdependent jobs into maintainable DAGs with a UI, automatic logging, retries, and notifications.
↳Container and Kubernetes workflows: Run Docker containers and Kubernetes Jobs as steps in workflows without building a custom control plane.
08

Alternatives

⚡Top VS:
VSDevFlow-Agent★49→VSrigour★29→VSheym★1.8k→VSagentrq★1.2k→
DevFlow-Agent logo
DevFlow-Agent★ 49
AI-powered development workflow automation tool
VSCompare→
rigour logo
rigour★ 29
The immune system for AI coding agents
VSCompare→
heym logo
heym★ 1.8k
Self-hosted AI workflow automation platform with visual canvas, agents, RAG, HITL, MCP, and observability in one runtime.
VSCompare→
agentrq logo
agentrq★ 1.2k
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents.
VSCompare→
zabbix-mcp-server logo
zabbix-mcp-server★ 255
MCP server for the complete Zabbix API — 220 tools, multi-server support, bearer auth, systemd ready. Works with ChatGPT, Claude, VS Code, Codex, JetBrains and any MCP client.
MikroMCP logo
MikroMCP★ 110
Production-grade MCP server for MikroTik RouterOS with secure AI-native network automation.
VSCompare→
apra-fleet logo
apra-fleet★ 108
AI agents that write code, review each other's work, and coordinate across your machines
VSCompare→
moo-tasks logo
moo-tasks★ 45
A simple multiuser multiboard task MCP server managed via kanban board interface. Created to allow simple self hosted agent task management.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
dagucloud /
dagu
↗

Single-binary workflow engine defined in YAML, with a web UI and MCP integration

4.6k402GPL-3.0
Last commit1d ago
StatusActive
CategoryWorkflow Automation
Contributors125
Latest releasev2.26.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.