agent-governance-toolkit
AI Agent Governance Toolkit, Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Runssource: GitHubPythonMITcommit 6b644564d112
Python, MIT licensed. The project labels itself: agent framework, ai agents, ai safety, compliance, governance, microsoft, owasp and policy engine.
agent-governance-toolkit runs. An Argusic agent installed it in 17 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All core Python packages install from source: agent-governance-toolkit-core, agent-governance-toolkit-cli, agent-control-specification (Rust wheel), agent-governance-toolkit-compliance. The agent-os test suite passes 2993/2993 selected tests, the ACS SDK test suite passes 306/306 selected tests, and the quickstart strict policy template correctly allows read_file and denies write_file.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- agent-control-specification <0.5.0,>=0.4.0b0 not on PyPI7 minutes
- Externally-managed Python environment prevents system-wide pip installs1 minute
- OPA binary not found (required by policy engine)1 minute
- SubprocessSandboxProvider tests fail because 'python' executable not found (only python3 exists)1 minute
- Install time
- 17 minutes
- Cold machine to finish
- 18 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- agent-os test suite: pytest tests/ -k 'not slow and not benchmark and not integration' => 2993 passed, 41 skipped, 0 failed. ACS SDK test suite: py.test tests/ => 306 passed, 41 skipped, 0 failed. Quickstart end-to-end: AgentControl.from_path('strict') + HostSession.input({'action':'read_file'}) => allow, input({'action':'write_file'}) => deny. OPA binary: opa version => Version: 1.4.2.
- Model tokens used
- 157,664
- Exact commit tested
- 6b644564d112
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
agent_sre path: /work/repo/venv/lib/python3.12/site-packages/agent_sre/__init__.py agent_sre.slo: OK agentmesh: OK All core imports verified exec /bin/sh -lc "python3 -c \"from datetime import datetime, timezone; print(datetime.now(timezone.utc)… succeeded in 0ms: 2026-09-29T01:33:49+0000 Now I have all the data I need. tokens used 157,664 Now I have all the data I need.
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 17 minutes to install, slower than the median of the 11 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 12 agent-framework projects Argusic has installed and timed, agent-governance-toolkit was the 10th fastest to reach a running state, and 7 of 12 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-frameworkai-agentsai-safetycompliancegovernancemicrosoftowasppolicy-enginepythonsecuritytrustzero-trust
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agent-governance-toolkit)Questions
- Does agent-governance-toolkit run?
- Yes. agent-governance-toolkit runs. Argusic installed and launched it on a clean machine in 17 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test agent-governance-toolkit?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6b644564d112. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test agent-governance-toolkit?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agent-governance-toolkit take to install?
- 17 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does agent-governance-toolkit need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agent-governance-toolkit?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does agent-governance-toolkit compare with the alternatives?
- Of the 12 agent-framework projects Argusic has installed and timed, agent-governance-toolkit was the 10th fastest to reach a running state, and 7 of 12 reached one at all.
- Where is the evidence for agent-governance-toolkit?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.