anti-slop vs numbat
The two are close in size: 1.7k stars for anti-slop, 1.0k for numbat. Over the days we have tracked them anti-slop moved +274.1% and numbat +27%, so anti-slop is growing faster right now.
They split the axes: anti-slop leads on model freedom, numbat on customization.
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
A rule-based filter with a mandatory PASS/FAIL Delivery Gate and liveliness toolkit focused on removing generic AI-generated UI and copy without prescribing visual style.
- Stars
- 1.7k
- Tracked growth
- +274.1%
- Maturity
- ●●●●●
- Last commit
- 17h ago
- Language
- JavaScript
- License
- MIT
- Cost to run
- Free to use; runs locally or via your agent/API
Performs endpoint-local detection and forensic reconstruction from on-disk session artifacts, letting operators evaluate agent activity with the same rule engine used for live enforcement.
- Stars
- 1.0k
- Tracked growth
- +27%
- Maturity
- ●●●●●
- Last commit
- 5d ago
- Language
- Go
- License
- Apache-2.0
- Cost to run
- Free, open-source local binary
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.
| Axis | anti-slop | numbat |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Diff + related files | ●●●●● Related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Hard gates + report | ●●●●● Severity gating |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Configurable skills & dials | ●●●●● Custom YAML rules |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Runs locally |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Any agent / BYOK | ●●●●● No model integration |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-command / npx | ●●●●● Single-binary install |
Which one to pick
Pick anti-slop if…
Easy setup — one-command picker or a single-file install drops a portable, non-prescriptive filter into many coding agents so you can stop AI 'slop' fast.
- Model freedom: Any agent / BYOK (5/5 against 1/5)
Pick numbat if…
Privacy-first — runs detection and rule evaluation on-device with a single-binary distribution, enabling monitoring and optional pre-action blocking without mandatory third-party services.
- Customization: Custom YAML rules (5/5 against 3/5)
What people want from each one
perplexityai/numbat
Questions people ask
Is anti-slop better than numbat?
They split the axes: anti-slop leads on model freedom, numbat on customization. anti-slop is worth picking when easy setup — one-command picker or a single-file install drops a portable, non-prescriptive filter into many coding agents so you can stop AI 'slop' fast.
Which of anti-slop and numbat keeps my code private?
anti-slop: Self-hostable (4/5). numbat: Runs locally (5/5).
What does each one cost to run?
anti-slop: Free to use; runs locally or via your agent/API. numbat: Free, open-source local binary.
Full profiles: miqdadbadjuber/anti-slop and perplexityai/numbat. Everything else in Security & guardrails.