Tooling Index / AI
← Browse tools

AI security & guardrails

garak

A scanner-style workflow that separates model connectors, adversarial probes, and response detectors.

AI security & guardrailsCLI / TUISDK / LibraryEvaluationMulti-provider
Website GitHub

Overview

Research summary

garak is an adversarial assessment toolkit for language models and conversational systems. Its command-line workflow connects model generators with probes that elicit problematic behavior and detectors that assess the responses. The project includes static, dynamic, and adaptive tests covering risks such as prompt injection, data leakage, toxicity, and hallucination. New generators, probes, and detectors can extend the framework. garak produces evidence for a security assessment; it is an offline testing tool rather than a request-blocking layer in an application.

Repository summary

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

AI security & guardrailsCLI / TUISDK / LibraryEvaluationMulti-provider

Pricing & services

Paid services unknown

Whether the provider offers paid products or services has not been established.

Licence scope

Apache-2.0

Implementation

Recorded implementation details and interfaces for garak.

Implementation details

Python vulnerability-scanning framework and command-line application

Languages
Python
Repository type
source

Recorded interfaces and capabilities

CLI / TUISDK / LibraryEvaluationMulti-provider

Licence scope

Apache-2.0

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

NVIDIA/garak ↗

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06

Documentation

Recorded references and research provenance for this entry.

Recorded sources 4

Research metadata

Research date
2026-10-02
Catalogue snapshot
2026-10-06

Community & social 3 channels

Communities

Social & updates