Collaboration: Governance node for Flowise agent workflows #6060
Description
Summary
We've built a governance integration for Flowise in the Agent Governance Toolkit (MIT, 6,100+ tests). The adapter lives at [\packages/agentmesh-integrations/flowise-agentmesh/](https://github.com/microsoft/agent-governance-toolkit/tree/main/packages/agentmesh-integrations/flowise-agentmesh).
What it provides
| Capability | Description |
|---|---|
| Policy enforcement | Allow/deny rules before every tool call (<0.1ms) |
| Trust scoring | Agent identity with trust tiers (0–1000) |
| Audit logging | Tamper-proof audit trail for compliance |
| Execution rings | 4-tier privilege model for flow nodes |
Integration approach
The adapter could work as a Flowise node or middleware — enforcing governance policies within visual agent flows. No breaking changes to existing chatflows.
Why this matters for Flowise users
- Enterprise readiness — organizations need governance before deploying AI agents
- OWASP coverage — addresses all 10 OWASP Agentic Top 10 risks
- Visual governance — policy nodes in the Flowise canvas
Open questions
- Would a governance node type be a good fit for the Flowise node library?
- Is there a preferred integration pattern for middleware components?
Happy to submit a PR or discuss the approach.