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
ML experiment tracking, visualization, and collaboration
Open source LLM engineering platform for tracing and analytics
Open-source library for evaluating and tracking LLM applications.
Open-source AI metadata tracker for logging and comparing ML experiments.
Open-source AI observability platform for tracing, evaluation, and experimentation.
CLI and library for testing, evaluating, and red-teaming LLM outputs.