Skip to main content
The user opens a pull request; CI runs Asqav to scan PraisonAI imports for governance patterns before merge.

Asqav Compliance Scanner

Asqav Compliance is a GitHub Action that scans Python files importing agent frameworks (including PraisonAI) and checks for five governance patterns on every PR.

Quick Start

1

Add the workflow file

Create .github/workflows/governance.yml in your repo:
2

Open a pull request

The scanner runs automatically on every PR and posts a compliance score as a PR comment.

What it checks

  • Audit Trail - logging, signed actions, audit records
  • Policy Enforcement - rate limits, scopes, permissions, guards
  • Revocation Capability - kill switches, suspend, terminate, circuit breakers
  • Human Oversight - approval flows, human-in-the-loop, confirmation gates
  • Error Handling - try/except blocks around agent operations

Setup

Add this to .github/workflows/governance.yml in your repo:
The action scans all Python files that import PraisonAI, LangChain, CrewAI, AutoGen, and other agent frameworks. It posts a compliance report as a PR comment with a score from 0 to 100.

Configuration

Example output

The action posts a Markdown report on each PR showing which files have governance coverage and which have gaps. Files importing agent frameworks without audit trails or error handling are flagged.

Best Practices

Set fail-on-gaps: true for production repos so governance gaps block merges rather than just warning.
Wrap agent.start() calls in try/except blocks to satisfy the Error Handling governance check.
Use Python logging around agent operations to satisfy the Audit Trail check.
Asqav posts a compliance score on every PR - include it in your code review checklist.

Custom Tools

Build your own agent tools

Tools Overview

Browse PraisonAI tool documentation