kitio.aiAdded Oct 28, 2026
Giskard
FreemiumRed teaming, evaluation and guardrails for LLM agents
What is Giskard?
Giskard tests AI agents and chatbots for security and quality problems such as prompt injection, data disclosure, sycophancy and wrongful refusals, then protects them in production. It serves enterprises in finance, healthcare and manufacturing as well as developers using its open-source library.
Continuous red teaming probes an agent through its API, and an autonomous agent audit has an AI agent attack your agent to find weaknesses. Evaluation checks answer quality so tightening security doesn't make responses worse, and guardrails block issues live.
Research projects include the Phare LLM benchmark and databases of real AI failures and harms. The core is open source for local experiments, with paid plans for enterprise use and a limited free offer of the agentic red teamer for startups.
Features
- Continuous red teaming
- Autonomous agent audit
- Agent evaluation
- Runtime guardrails
- Open-source library
Tags
Releases
+ Submit new release- Listed
Giskard was added to the directory.
Organization
Giskard
🇫🇷 France
Listed by kitio.ai · unverified owner
Pricing
- Pricing model
- Freemium
- Paid options from
- Not listed
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.
Top Giskard alternatives
View allModels & APIs
Open-source CLI for testing prompts and red-teaming AI apps
Models & APIs
Security platform protecting GenAI apps and agents from prompt attacks
Models & APIs
Automated red teaming and security testing for AI models and agents
Models & APIs
LLM evaluation, testing and monitoring platform for production AI
If you liked Giskard
Open-source Python library for testing and evaluating LLM apps
FreeModels & APIsMade in United KingdomThe main hub for open models, datasets and AI demo apps
Freemium · $9/moModels & APIsMade in United StatesRun open models locally with one command, plus optional cloud models
Freemium · $20/moModels & APIsMade in United StatesOpen-source library for similarity search over dense vectors
FreeModels & APIsMade in United States
Pros and cons
Pros
- Open-source option for local testing
- Covers both security and quality
- Works with any agent API
Cons
- Enterprise pricing not listed
- Full platform needs a demo
- Free red-teaming offer is limited
Prompts & results
No prompts yet. Add your own prompt and output to help others use this tool.
Share a prompt
Reviews
Q&A
What is Giskard?
Giskard tests AI agents and chatbots for security and quality problems such as prompt injection, data disclosure, sycophancy and wrongful refusals, then protects them in production. It serves enterprises in finance, healthcare and manufacturing as well as developers using its open-source library.
How much does Giskard cost?
Giskard is freemium.
Is there a free version of Giskard?
Yes. Giskard has a free plan, and paid plans add more usage and features.
What are the main features of Giskard?
Continuous red teaming, Autonomous agent audit, Agent evaluation, Runtime guardrails, Open-source library.
Who makes Giskard?
Giskard is made by Giskard.
What are the best alternatives to Giskard?
Popular alternatives include Promptfoo, Lakera, Mindgard.