Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Security
  4. /
  5. Giskard
Security
Giskard icon

Giskard

by Giskard

Giskard is an open-source Python library for testing and evaluating AI agents. It covers eval checks, LLM-as-judge scoring and automated red teaming.

Web app·Freemium

View on GitHub(opens in a new tab)

About Giskard

Key features of Giskard

  • Scenario, check and suite API for agent evals
  • LLM-as-judge checks including Groundedness and Conformity
  • Multi-turn conversation testing
  • Vulnerability scan for red teaming across OWASP LLM Top-10 categories
  • Built-in dataset of prompt-injection payloads
  • Quality scan for RAG knowledge bases
  • Custom scenario generators
  • Optional telemetry with an opt-out setting

Who Giskard is for

  • Developers testing LLM agents and RAG systems
  • Teams adding regression checks for AI behavior
  • Security-minded teams red teaming chatbots
  • Python engineers evaluating non-deterministic outputs

How to use Giskard

  1. 1

    Step 1: Install with pip install giskard (Python 3.12 or later is required).

  2. 2

    Step 2: Add a provider extra such as giskard[openai] and set its API key if you use LLM judges.

  3. 3

    Step 3: Wrap your model or agent as a callable target.

  4. 4

    Step 4: Build a Scenario with interact and check steps, then call run_sync or await run.

  5. 5

    Step 5: Install giskard[scan] and run vulnerability_scan with a description of your agent to generate adversarial tests.

  6. 6

    Step 6: Read the printed report and fix failing behavior.

Giskard FAQ

What changed in Giskard v3?

It is a fresh rewrite for dynamic, multi-turn testing of agents, with fewer heavy dependencies. v2 remains available but is not actively maintained.

Do LLM judges need an API key?

Yes. Judges and scan generators need a provider extra installed and the matching API key.

Does Giskard collect data?

It has optional aggregated telemetry and says no prompts or outputs are sent. You can opt out with DO_NOT_TRACK=1 or GISKARD_TELEMETRY_DISABLED=1.

Can it test ML models?

Yes. The README says you can wrap an ML model as a target. The automatic tabular scan remains v2-only.

Details

Pricing
Freemium
Type
Web app
Categories
SecurityResearch
Added
Sep 16, 2026
Giskard iconPublisherGiskard

Built from public sources

We put this page together from Giskard’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with Giskard.

Work at Giskard? Claim the listing to manage it yourself.

Something wrong here?

Related tools

See more
Arthur AI iconArthur AIArthur · Contact for pricingArthur AI uses AI for AI monitoring and evaluation platform for model performance, LLM observability, guardrails, and governance.Security · Contact for pricingWhyLabs iconWhyLabsWhyLabs · FreemiumWhyLabs uses AI for AI observability platform for monitoring model and LLM behavior, data quality, safety, and production anomalies.Security · FreemiumFiddler AI iconFiddler AIFiddler AI · Contact for pricingFiddler AI uses AI for AI observability and governance platform for monitoring model performance, safety, explainability, and application behavior.Security · Contact for pricing