ActiveSpecialisedOpen Source, Apache-2.0
Apache Airflow
Workflow orchestration
Apache Airflow is an open-source tool for orchestrating data and ML pipelines defined as DAGs in Python. It is not an agent framework, but it is often used to integrate LLM tasks and agent runs into existing data processes on a schedule and with full traceability. Provider packages make services such as OpenAI or Cohere available.
Not in the directory
Apache Airflow is no longer listed or recommended
Airflow orchestrates data pipelines. Agents can only be chained as individual tasks in a DAG.
Good fit if
Focus: Data engineering and data science teams
- your project is about ML pipelines, Data engineering or ETL
- someone on your team writes code
Probably not if
- nobody on your team writes code (1/5 for use without developers)
- your team is just getting started with agents (skill level: Advanced)
- there is little time for training (learning curve: steep)
Key figures
- Usable without developers
- 1/5
- Scalability
- 5/5
- Integrations
- 5/5
- Versioning
- 4/5
- Observability
- 4/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- Specialised
- Type
- Workflow orchestration
- Licence
- Open Source (Apache-2.0)
- Pricing
- Open SourceOpen source and free (Apache 2.0), managed offerings from cloud providers
- Deployment
- Self-Hosted, Cloud, Kubernetes
- Models
- Über Provider-Pakete (z. B. OpenAI, Cohere)
- RAG
- No
- Multi-Agent
- Possible
- SSO, roles (RBAC)
- SSO yes, RBAC yes
- Latest version
- 3.3.2
- GitHub stars
- 47,000
Key features
- DAGs in Python
- ML pipelines
- Scheduling
- Many provider packages
Typical use cases
- ML pipelines
- Data engineering
- ETL
Implementation
Get Apache Airflow implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- DeveloperAgno (Phidata)Agno, formerly Phidata, is a Python framework for agents and multi-agent teams with memory, knowledge bases and guardrails. AgentOS lets you serve agents as an API in your own cloud, and a control plane is used for testing, tracing and monitoring. The framework is licensed under Apache 2.0, while the hosted control plane is paid.View profile
- DeveloperAutoGenAutoGen is an open-source framework from Microsoft Research for multi-agent systems, known for group chats between agents and code execution. With the release of Microsoft Agent Framework 1.0 in April 2026, AutoGen entered maintenance mode: it only receives bug fixes and security updates, and new development happens in Agent Framework. Microsoft recommends Agent Framework for new projects.View profile
- InfrastructureBrowser UseBrowser Use is a Python library that lets AI agents operate websites through natural language: clicking, filling in forms, extracting data. Browser Use Cloud adds hosted stealth browsers, proxies and CAPTCHA solving, plus its own model trained for browser tasks. The library is MIT licensed.View profile
- DeveloperElizaOSElizaOS is an open-source TypeScript framework for autonomous agents with personality, memory and plugins. Agents can connect to Discord, X, Telegram and other platforms, and more than 200 plugins extend their capabilities up to blockchain applications. Multiple agents can collaborate through a shared message bus.View profile