kelkalot/simpleaudit

Allows to red-team your AI systems through adversarial probing. It is simple, effective, and requires minimal setup.

50
/ 100
Established

Provides multilingual scenario-based adversarial probing with support for both local models (via Ollama, Llama.cpp, LM Studio) and API-hosted providers, using a separate judge model to evaluate responses. Built-in safety scenarios and extensible framework allow custom test creation, with results visualized through an interactive web dashboard and comparable across multiple models simultaneously.

Used by 1 other package. Available on PyPI.

Maintenance 10 / 25
Adoption 9 / 25
Maturity 18 / 25
Community 13 / 25

How are scores calculated?

Stars

6

Forks

2

Language

Python

License

MIT

Last pushed

Feb 24, 2026

Monthly downloads

40

Commits (30d)

0

Dependencies

2

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/kelkalot/simpleaudit"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.