Issue Station
Sign In
Tools hereToolbox

autogen - 💡(How to fix) Fix Kevros Governance tools — action verification + hash-chained audit trails for AutoGen agents [7 comments, 3 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
microsoft/autogen#7247•Fetched 2026-04-08 00:40:05
View on GitHub
Comments
7
Participants
3
Timeline
11
Reactions
0
Author
jmcgraw434jmcgraw434
Participants
jmcgraw434jmcgraw434Kelisi808Kelisi808mikeargentomikeargento
Timeline (top)
commented ×7mentioned ×2subscribed ×2

Code Example

pip install kevros
RAW_BUFFERClick to expand / collapse

Kevros Governance Integration for AutoGen

Governance-as-a-service for AutoGen agents. Verify actions before execution, maintain independently verifiable evidence trails, and generate compliance evidence bundles.

Integration

OpenAI-compatible function definitions ready to use with AutoGen agents: https://github.com/ndl-systems/kevros-governance-sdk/blob/main/openai_tools.json

Python SDK:

pip install kevros

What it provides

  • Pre-execution action verification against policy bounds
  • Signed, independently verifiable evidence records (ML-DSA-87 / FIPS 204)
  • Intent-command-outcome binding (prove what agent intended vs did)
  • Compliance evidence bundles (auditor-grade)

Use case

Multi-agent workflows where agents take real-world actions (trades, API calls, deployments) and need to prove what happened for compliance, audit, or legal purposes.

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

extent analysis

Fix Plan

To integrate Kevros Governance with AutoGen, follow these steps:

  • Install the Kevros Python SDK:
pip install kevros
  • Import the Kevros SDK in your Python script:
import kevros
  • Define your OpenAI-compatible function using the Kevros SDK:
def verify_action(action):
    # Initialize Kevros client
    client = kevros.Client()
    
    # Verify action against policy bounds
    verification_result = client.verify_action(action)
    
    return verification_result
  • Use the verify_action function to verify actions before execution:
action = {"intent": "make_trade", "params": {"symbol": "AAPL", "quantity": 10}}
verification_result = verify_action(action)
if verification_result.allowed:
    # Execute the action
    print("Action allowed and executed")
else:
    # Handle denied action
    print("Action denied")

Verification

To verify that the fix worked, test the verify_action function with different actions and policy bounds. Check that the function correctly allows or denies actions based on the policy.

Extra Tips

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#installation#tensor shape#autograd error#tool integration#LLM response#prompt template#agent execution

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

autogen - 💡(How to fix) Fix Kevros Governance tools — action verification + hash-chained audit trails for AutoGen agents [7 comments, 3 participants]