agentic_security vs stop-that-shit

The two are close in size: 2.0k stars for agentic_security, 1.6k for stop-that-shit.

They split the axes: agentic_security leads on model freedom and setup ease, stop-that-shit 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

Agentic Security focuses on agent/workflow-focused, multimodal (text, image, audio) and multi-step attack/fuzzing capabilities (including RL-based and dataset mutation approaches) to evaluate LLM vulnerabilities beyond single-shot prompt tests.

Stars
2.0k
Tracked growth
+4.7%
Maturity
Last commit
3d ago
Language
Python
License
Apache-2.0
Cost to run
Your LLM API key, usage billed by the provider

Implements executable, evidence-backed Guards and Skills that intercept unrequested hashes, dependency/subagent launches and scope creep across multiple agent hosts, turning policy statements into machine-enforceable checks.

Stars
1.6k
Tracked growth
not tracked long enough
Maturity
Last commit
2d ago
Language
JavaScript
License
MIT
Cost to run
Free, local install; uses the host agent's model access (may require provider subscriptions).
0%+240%69 tracked days
msoedov/agentic_securitylennney/stop-that-shit

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.

Axisagentic_securitystop-that-shit
Context depth
How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository.
Prompt-only
Diff + related files
Noise control
How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only.
Thresholds/config
Armed / observing gating
Customization
How far it bends to your team: custom rules, prompts, style guides, per-path config.
Config + modules
Command flags & policies
Privacy
Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only.
Self-hostable
Self-hostable
Model freedom
Whether you can point it at any provider, or it is wired to one.
Bring-your-own-key
Multiple specific providers
Setup ease
What it takes to get a first useful run out of it.
One-command start
Install + restart

Which one to pick

Pick agentic_security if…

Easy setup — pip-installable and runnable locally with configurable datasets and modules to quickly run multimodal, multi-step vulnerability scans against your LLM endpoints.

  • Model freedom: Bring-your-own-key (5/5 against 3/5)
  • Setup ease: One-command start (5/5 against 3/5)
Runs in github-action, ci, cli, web-app. Works with byok, openai.

Pick stop-that-shit if…

Privacy-first — a local-first plugin that enforces task-boundary guardrails across Codex, Claude Code, OpenCode and Hermes Agent CLI without relying on a centralized service.

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

What people want from each one

Questions people ask

Is agentic_security better than stop-that-shit?

They split the axes: agentic_security leads on model freedom and setup ease, stop-that-shit on context depth. agentic_security is worth picking when easy setup — pip-installable and runnable locally with configurable datasets and modules to quickly run multimodal, multi-step vulnerability scans against your LLM endpoints.

Which of agentic_security and stop-that-shit keeps my code private?

agentic_security: Self-hostable (4/5). stop-that-shit: Self-hostable (4/5).

What does each one cost to run?

agentic_security: Your LLM API key, usage billed by the provider. stop-that-shit: Free, local install; uses the host agent's model access (may require provider subscriptions)..

Full profiles: msoedov/agentic_security and lennney/stop-that-shit. Everything else in Security & guardrails.