Projects
Inspect AI PyPI GitHub
Framework for systematic evaluation of large language models, built by the UK AISI in collaboration with Meridian.
Inspect Scout PyPI GitHub
In-depth analysis of AI agent transcripts with rich visualization of results and high-performance parallel scanning.
Petri GitHub
Automated alignment auditing tool that orchestrates multi-turn interactions, built in collaboration with Anthropic and UK AISI.
Inspect Flow PyPI GitHub
Workflow orchestration for Inspect AI that enables running evaluations at scale with repeatability and maintainability.
Inspect SWE PyPI GitHub
Makes software engineering agents like Claude Code and Codex CLI available as standard Inspect Agents for evaluation.
Inspect Harbor PyPI GitHub
Interface to run [Harbor](https://harborframework.com/registry) tasks using Inspect AI. Includes over 40 agentic datasets including swebenchpro, terminal-bench-pro, and replicationbench.
Inspect Viz PyPI GitHub
Data visualization library for creating high-quality interactive visualizations from Inspect AI evaluation results.
Inspect VSCode Marketplace GitHub
Visual Studio Code extension for productive use of Inspect AI with an integrated log viewer, task browser, and debugging tools.