agent-governance-toolkit vs cc-safety-net

agent-governance-toolkit is much bigger: 6.2k stars against 1.5k. Over the days we have tracked them agent-governance-toolkit moved +51.2% and cc-safety-net +2.9%, so agent-governance-toolkit is growing faster right now.

They split the axes: agent-governance-toolkit leads on model freedom, cc-safety-net on context depth.

Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.

Where they stand today

Deterministic, application-level enforcement that intercepts every tool call and makes denied actions structurally impossible (fail-closed governance plus tamper-evident audit), rather than relying on prompt-level controls.

Stars
6.2k
Tracked growth
+51.2%
Maturity
Last commit
1d ago
Language
Python
License
MIT
Cost to run
Free, open-source

Parses command semantics (including shell wrappers and interpreter one-liners) to block destructive commands and secret access before they execute across many coding agent CLIs.

Stars
1.5k
Tracked growth
+2.9%
Maturity
Last commit
56m ago
Language
TypeScript
License
MIT
Cost to run
Free, local install (requires Node.js)
0%+51%90 tracked days
microsoft/agent-governance-toolkitkenryu42/cc-safety-net

Six axes, head to head

Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.

Axisagent-governance-toolkitcc-safety-net
Context depth
How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository.
Action-level only
Command + related files
Noise control
How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only.
Approval gating
Presets + audit
Customization
How far it bends to your team: custom rules, prompts, style guides, per-path config.
YAML & APIs
Rulebooks & per-project
Privacy
Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only.
Fully local runnable
Local-only
Model freedom
Whether you can point it at any provider, or it is wired to one.
Bring-your-own key
Multiple agent CLIs
Setup ease
What it takes to get a first useful run out of it.
One-command start
One-command install

Which one to pick

Pick agent-governance-toolkit if…

Deterministic enforcement — pick AGT when you need fail-closed, application-level policy enforcement and tamper-evident auditing that prevents agents from performing denied actions.

  • Model freedom: Bring-your-own key (5/5 against 3/5)
Runs in pr-bot, github-action, ci, cli, ide, coding-agent-plugin, web-app. Works with byok.

Pick cc-safety-net if…

Safety-first — Blocks destructive git/filesystem commands and secret access before AI agents run them, using semantic command analysis, configurable rulebooks, presets, and a local audit trail.

  • Context depth: Command + related files (3/5 against 1/5)
Runs in cli, coding-agent-plugin, web-app. Works with other-fixed.

What people want from each one

Questions people ask

Is agent-governance-toolkit better than cc-safety-net?

They split the axes: agent-governance-toolkit leads on model freedom, cc-safety-net on context depth. agent-governance-toolkit is worth picking when deterministic enforcement — pick AGT when you need fail-closed, application-level policy enforcement and tamper-evident auditing that prevents agents from performing denied actions.

Which of agent-governance-toolkit and cc-safety-net keeps my code private?

agent-governance-toolkit: Fully local runnable (5/5). cc-safety-net: Local-only (5/5).

What does each one cost to run?

agent-governance-toolkit: Free, open-source. cc-safety-net: Free, local install (requires Node.js).

Full profiles: microsoft/agent-governance-toolkit and kenryu42/cc-safety-net. Everything else in Security & guardrails.