Skip to content

Python: Kevros Governance plugin — action verification + audit trails for SK agents #13574

@knuckles-stack

Description

@knuckles-stack

Kevros Governance Plugin for Semantic Kernel

Governance-as-a-service for Semantic Kernel agents. Cryptographic action verification (ALLOW/CLAMP/DENY), hash-chained provenance, intent-command binding, and compliance bundles.

OpenAI Function Definitions (ready to use)

Pre-built function calling definitions for Semantic Kernel's OpenAI integration:
https://github.com/ndl-systems/kevros-governance-sdk/blob/main/openai_tools.json

Python SDK

```
pip install git+https://github.com/ndl-systems/kevros-governance-sdk.git
```

Use Case

SK agents taking real-world actions (enterprise workflows, data mutations, API calls) where you need tamper-evident proof of what the AI decided. EU AI Act, NYC Law 144, SOC2 audit compliance.

Gateway: https://governance.taskhawktech.com
A2A Agent Card: https://governance.taskhawktech.com/.well-known/agent.json

Metadata

Metadata

Assignees

No one assigned

    Labels

    pythonPull requests for the Python Semantic Kerneltriage

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions