Agent Governance ToolkitAgent Governance Toolkit 4.1.0 · Python 3.10+
Dashboard
0%

What installing gives you

The install is one name over five distributions and twenty-three import packages, of which a reader touches about five and six do not import at all on a bare setup.

Last updated: 14 Oct, 2026 · Agent Governance Toolkit 4.1.0

The setup lesson installed the toolkit with one command. That command pulled in far more than the course uses. Knowing what landed, and what quietly failed to import, saves an hour of confusion later.

Listing the core packages

The twenty-three core import packages carry these names. Most import; a handful raise, because they need an optional dependency a bare install does not pull in, or because of a bug in the package itself.

python
core = ["agent_compliance","agent_control_plane","agent_os","agent_os_observability",
        "agent_primitives","agent_runtime","agentmesh","amb_core","atr","caas",
        "cmvk","emk","hypervisor","iatp","mcp_kernel_server","nexus",
        "agent_sandbox","agent_sre","mcp_trust_server",
        "a2a_agentmesh","agent_mcp_governance","mcp_receipt_governed","mcp_trust_proxy"]

Counting what imported

Trying to import each name and sorting the results shows the real picture at a glance.

ExampleSeventeen of twenty-three import on a bare setup
import importlib

# import each package, split the names into those that load and those that raise
ok, fail = [], []
for name in core:
    try:
        importlib.import_module(name)
        ok.append(name)
    except Exception as e:
        fail.append((name, str(e).split("No module named")[-1].strip()))

print(f"packages {len(core)}  import OK {len(ok)}  import FAIL {len(fail)}")
for name, why in fail:
    print(f"  {name:22} missing {why}")

What the failures mean

  • Five failures are missing optional dependencies. prometheus_client, aiofiles, numpy and fastapi are not pulled in by a bare install; the course never needs those five packages.
  • One failure is a real bug. agent_mcp_governance tries to import agent_os.governance, a module that does not exist in 4.1.0. No dependency fixes it.
  • Everything the course uses is in the seventeen that import. You do not need the broken ones.

The five packages the course touches

PackageWhat you use it forTaught in
agent_osgovern(), YAML policy, the JSONL audit loggergovern(): the smallest real gate and Writing a policy in a YAML file
agent_control_planeintercept_tool_execution, the policy engine, the flight recorderOne choke point for every tool call
agentmeshagent identity, delegation, the Merkle audit chainAn agent that can prove who it is
mcp_trust_proxygoverning an MCP serverA trust proxy for an MCP server
agent_srecircuit breakers and an error budgetCircuit breakers and an error budget

Where the import map helps

  • Debugging an ImportError on a fresh machine, to tell a missing optional dependency from a real bug.
  • Trimming a deployment, installing only the layers you use rather than every package.
  • Reading the toolkit's own code, knowing which packages are live and which are stubs.
Watch out. An ImportError from one of these packages does not mean your install is broken. Five of them need a dependency the course does not use, and one is broken in the release itself. Import what you need and leave the rest.
Try it yourself
  • Install numpy and re-run the check. Watch cmvk and emk move into the OK list.
  • Import agent_mcp_governance on its own and read the full traceback that names the missing module.
  • Print the OK list and find the five packages the table says the course uses.

Little by little, you're building something great.