Inspect AI
UK AI Security Institute framework for large language model evaluations and benchmarks.
About
Inspect AI is a framework for large language model evaluations created by the UK AI Security Institute. It provides built-in components for prompt engineering, tool usage, multi-turn conversations, and model-graded evaluation. The project ships 200+ pre-built evaluations and supports extension via Python packages for custom elicitation and scoring.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Observability & Evaluation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- MIT
- Added
- May 7, 2026
Related Tools
Open source LLM engineering platform for tracing and analytics
Open source platform for the ML lifecycle
AI observability and evaluation from Arize
ML experiment tracking, visualization, and collaboration
Open-source AI metadata tracker for logging and comparing ML experiments.
CLI and library for testing, evaluating, and red-teaming LLM outputs.