behive

n8n community node for BeHive — deep research engine that builds knowledge graphs

Package Information

Released: 2 mo ago
Downloads: 0 weekly / 0 monthly
Latest Version: 0.1.0

Documentation

n8n-nodes-behive

This is an n8n community node for BeHive — the open-source deep research engine that extracts structured claims and builds knowledge graphs.

n8n is a fair-code licensed workflow automation platform.

Installation

Follow the installation guide in the n8n community nodes documentation.

npm package name: n8n-nodes-behive

Nodes

BeHive

Execute research operations:

Operation Description
Research → Start Launch a deep research mission on any topic
Research → Start and Wait Start and poll until done (returns full report)
Knowledge → Search Claims Search verified claims across all missions
Knowledge → Get Entities Get entities from the knowledge graph
Mission → Get Status Check progress of a running mission
Mission → Get Report Get the synthesized report
Mission → List List all research missions

The BeHive node is usable as a tool — connect it to an AI Agent node and let the agent decide when to research!

BeHive Trigger

Poll-based trigger that fires when:

  • Mission Completed — any research finishes successfully
  • Mission Failed — a mission encounters an error
  • Quality Alert — mission achieves quality above your threshold

Credentials

Field Description
Base URL Your BeHive instance URL (default: http://localhost:8091)
API Key Optional API key for authenticated instances

Example Workflows

1. Research on Schedule

Schedule Trigger (daily) → BeHive (Start and Wait) → Email/Slack/Telegram

2. AI Agent with Research Capability

Chat Trigger → AI Agent
                  └─ BeHive Tool (Research → Start and Wait)
                  └─ BeHive Tool (Knowledge → Search Claims)

3. Continuous Intelligence Pipeline

BeHive Trigger (Mission Completed) → Format Report → Store in Notion/Airtable → Notify Team

Compatibility

  • n8n version: 1.0+
  • Node.js: 18.10+
  • BeHive API: 0.1.0+

Resources

License

MIT

Discussion