Giskard
Paris, France
Founded 2021
Giskard is an AI red teaming and testing platform that helps companies detect security vulnerabilities, hallucinations, and quality issues in LLM-based agents before deployment. Its open-source Python library and enterprise hub provide automated scanning, evaluation, and continuous testing capabilities for AI systems ranging from RAG pipelines to traditional machine learning models.
Websites:
Last Updated: March 13, 2026
Current Valuation
No valuation data available
Funding Summary
$6.6M
Total reported funding
Announcement
February 19, 2025
Giskard Blog: Giskard announces Phare, a new open & multi-lingual LLM Benchmark
Media Mention
November 14, 2023
TechCrunch: Giskard’s open source framework evaluates AI models before they’re pushed into production
Key People
Core OSS Projects
Open-source evaluation and testing framework for AI systems, covering LLM agents and traditional ML models
License: Apache-2.0
Business Information
Technologies
Red Teaming
AI evaluation
Machine Learning
AI Security
LLM Testing
Sectors
Enterprise
Licenses
Apache-2.0
Socials and Communities
Cossmology Badge
COSS Weekly Newsletter
Stay up to date with the latest news, funding rounds, and announcements from the COSS universe.
Check out COSS Weekly on the web