FlowDrop Agents bridges Drupal’s AI Agents with FlowDrop workflows, allowing you to execute AI agents as workflow nodes with full status tracking, structured output, and robust error handling.
With this module, any agent from the AI Agents ecosystem can be run directly inside a FlowDrop workflow. Agents become first-class workflow nodes, making it easy to automate content creation, configuration changes, conversational flows, and complex multi-step AI tasks in Drupal.
This module was born during the Drupal AI Hackathon - Play to Impact 2026, organized by the European Commission.
Key Features
- AI Agent Executor Node
Adds a FlowDrop node that executes any AI Agent (plugin-based or config-based). - Full Status Tracking
Tracks execution states such as Solvable, Needs Answers, Informs, and more. - Structured Output
Returns detailed data about created, edited, or deleted configs and content entities. - Chat History Support
Pass conversation context to agents for multi-turn interactions. - Error Handling & Metadata
Clear success flags, error messages, and execution metadata for reliable workflows. - Direct vs Blueprint Mode
Choose whether agents create entities immediately or return blueprints for review. - Dynamic Agent Discovery
Automatically discovers all available AI Agents on your site.
Typical Use Cases
- Generate and update content with AI directly inside workflows
- Build conversational agents with memory using chat history
- Automate site building tasks with structured, auditable output
- Chain multiple AI agents together with conditional logic
Contributing
The FlowDrop Agents module's issue queue is intended for reporting bugs, submitting feature requests, and planning.
Additionally, you can join the #flowdrop channel on Drupal Slack.
Supporting organizations:
Supporting Development
Initial development
Project information
- Project categories: Artificial Intelligence (AI), Content editing experience, Integrations
- Ecosystem: AI (Artificial Intelligence)
4 sites report using this module- Created by joevagyok on , updated
Stable releases for this project are covered by the security advisory policy.
Look for the shield icon below.
