- Home
- LLM Evaluation Tools
- garak
On the recordRead 7 Oct 202612 facts
garak
Plans and prices
Free
Free
Free tool · open-source software
Read 7 Oct 2026 · github.com
On the record
- Automated scans
- garak can run a standard scan and produce a report without supervision, while allowing scan configuration to be customized.docs.garak.ai · read 7 Oct 2026
- Deployment
- garak is a command-line tool developed in Linux and OSX and can be installed with pip or from source.github.com · read 7 Oct 2026
- Integrations
- The project lists support for OpenAI, Hugging Face, Cohere, Replicate, AWS Bedrock, LiteLLM, REST-accessible models, and custom Python integrations.github.com · read 7 Oct 2026
- Local and hosted models
- The documentation describes running Hugging Face models locally or accessing them through an inference API or private endpoint.github.com · read 7 Oct 2026
- Maintainer
- The project website says garak is backed by NVIDIA and is updated by NVIDIA and the community.garak.ai · read 7 Oct 2026
- Output scope
- The reference documentation says garak supports mainstream any-to-any large models but assesses text output only.reference.garak.ai · read 7 Oct 2026
- Probe and detector design
- Probes attempt to elicit failures, and detectors examine model outputs for failure modes such as unsafe content or failure to refuse.reference.garak.ai · read 7 Oct 2026
- Purpose
- garak is an LLM vulnerability scanner that probes language models and systems using them for security weaknesses.garak.ai · read 7 Oct 2026
- Reports
- garak produces screen output, a detailed report log, a hit log, and a debug log.docs.garak.ai · read 7 Oct 2026
- Security reporting
- The repository directs security vulnerability reports to NVIDIA’s security submission form or [email protected] and says not to report them through GitHub.github.com · read 7 Oct 2026
- Support
- The project points users to its user guide, reference documentation, Discord, GitHub issues, and an NVIDIA email address for support.garak.ai · read 7 Oct 2026
- Threat coverage
- The project lists hallucination, data leakage, prompt injection, misinformation, toxicity generation, and jailbreaks among the weaknesses it probes.github.com · read 7 Oct 2026