dagu
Dagu is a local-first workflow engine that transforms existing scripts and commands into reliable workflows via YAML files.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 3.7k
- Source
- GitHub
- Added
- 2026-08-01
- Last verified
- 2026-08-01

Overview
Dagu is a local-first workflow engine that converts existing scripts and commands into reliable workflows. It offers scheduling, retry mechanisms, approval processes, logging, and a Web UI without requiring external databases or message brokers. Users can define workflows using simple YAML files and manage and monitor them via command line or Web interface. Dagu is suitable for developers and teams needing task automation, especially for ETL data operations, legacy script and cron job management, and media conversion scenarios.
Key features
- ▪Supports existing scripts and commands unchanged
- ▪YAML files define dependencies, scheduling, and retries
- ▪Built-in Web UI to view status and logs
- ▪Single binary file, no external services required
Use cases
Pros
- +Easy to install and use
- +No external database required
- +Supports multiple platforms
- +Built-in Web UI
Limitations / notes
- -Requires internet to download installation
- -Higher learning curve
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
Is it free?
Yes, Dagu is open-source and free.
Does it support Chinese?
The documentation is primarily in English, but the interface supports multiple languages.
Can it be used commercially?
Yes, Dagu is an open-source project and allowed for commercial use.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.