Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience real numbers from our own analytics — open to see them
–Visitors
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · counted by iTechGuides's own first-party analytics, bots removed, every figure rounded down · how we count

Augustus

Free#16 of 29 in AI Security Testing Tools

Augustus: A portable Go scanner for probing LLMs across attacks, providers, and custom endpoints. Ranked #16 of 29 in AI Security Testing Tools by our editors (7.6/10); pricing: Open source; best for portable security probe automation.

7.6/10Editor score
Visit Augustus
Augustus7.6 Visit Augustus

At a glance

  • Editor score
    7.6 / 10
  • Pricing
    Open source
  • Best for
    Portable security probe automation
  • Paid from
    None
  • Prompt injection tests
    Yes
  • Founded
    2010 · Austin, Texas, United States
  • Facts checked
    21 Sep 2026
Augustus screenshot

  • Where it wins

    • 210+ probes across jailbreak, injection, extraction, agent, and safety tests
    • 28 provider categories, 43 generator variants, and 90+ response detectors
    • Single Go binary with concurrent scanning, custom REST tests, and report exports

  • Where it doesn't

    • Self-hosted deployment requires security teams to manage the environment
    • Broad provider and probe coverage may require configuration for each target
    • The published details do not describe platform coverage or paid support tiers

Our verdict on Augustus

Augustus is an open-source, Go-based LLM vulnerability scanner from Praetorian Security, Inc. It is designed for security professionals conducting authorized production testing of large language models. The tool covers prompt injection, jailbreaks, data extraction, encoding exploits, agent attacks, unsafe outputs, and safety-benchmark scenarios. Its self-hosted deployment model and single portable binary suit teams that want to run security probes within their own testing environments.

Its main strength is breadth within adversarial LLM testing. Augustus provides 210+ vulnerability probes, 90+ response detectors, and prompt transformations for encoding, paraphrasing, poetry, translation, and case changes. The detectors include pattern matching, LLM-as-a-judge, and unsafe-content detection. Integrations span 28 LLM provider categories and 43 generator variants, including OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Google Vertex AI, Cohere, Replicate, HuggingFace, Together AI, Anyscale, Groq, Mistral, Fireworks, DeepInfra, and NVIDIA NIM. That combination makes it a fit for teams comparing behavior across hosted or local model setups.

Operational flexibility is another defining feature. Concurrent scanning includes rate limiting, retries, and timeout handling, while custom REST endpoint testing supports request templates and response extraction. Results can be exported as table, JSON, JSONL, or HTML reports, and plugin-style extensibility supports additional customization. Teams that need a portable, scriptable scanner with varied probes and provider connections should consider Augustus. It is less suitable for buyers seeking a managed platform, a described enterprise support tier, or a product centered on general AI governance rather than security testing.

Augustus pricing

Plans Open sourceFree Free to use — no paid tier required for the core job.
See plans on github.com

Augustus fact sheet

Free planNot verified
Paid fromNone
Prompt injection testsYes
Jailbreak testsYes
Data leakage testsYes
Unsafe output testsYes
Custom test casesYes
Deployment modeSelf_hosted
DeploymentSelf-hosted
SupportEmail, Community, Docs
Built forMid-market, Enterprise (editorial estimate)
Integrations28+ integrations: OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Google Vertex AI, Cohere …
PricingOpen source
Websitegithub.com
Facts checked21 Sep 2026

Augustus integrations

Augustus lists 28+ integrations on its own site — the 20 named here are the ones its pages call out.

  • OpenAI
  • Anthropic
  • Azure OpenAI
  • AWS Bedrock
  • Google Vertex AI
  • Cohere
  • Replicate
  • HuggingFace
  • Together AI
  • Anyscale
  • Groq
  • Mistral
  • Fireworks
  • DeepInfra
  • NVIDIA NIM
  • NVIDIA NeMo
  • NVIDIA NVCF
  • NeMo Guardrails
  • IBM watsonx
  • LangChain

Alternatives to Augustus

See all Augustus alternatives →

Used Augustus? Be the first to review it

The editor score above is our own research. What this page doesn't have yet is a reader's view — what you used Augustus for, what worked and what didn't. No stars are seeded and no review is paid for; an editor reads every one before it appears.

Write a reviewTwo minutes · verified accounts only · read by an editor before it appears

Reviews come only from verified accounts. Sign in or create an account first — your e-mail is never shown.

Your rating

0 characters · at least 80, up to 3,000

Posted from your verified account. Reviews appear after an editor reads them, usually within two working days.

Featured on iTechGuides

Featured on iTechGuides — Augustus 7.6/10

Augustus is listed in our AI Security Testing Tools directory. Add the badge to your site — it links back to this page.

<a href="https://www.itechguides.com/products/augustus/"><img src="https://www.itechguides.com/best/badge/augustus.svg" alt="Featured on iTechGuides" width="230" height="46"></a>

Guides on AI security testing tools

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

Advertiser disclosure: iTechGuides is reader-supported. We may earn a commission when you click some links. How we rank.

Last updated · How we research and update