# Inspect Robots

Inspect Robots is the open-source evaluation framework for physical AI and VLA (vision-language-action) models: the "Inspect AI for robotics". A benchmark is a Task (dataset of Scenes + scorers) run against two swappable inputs: a Policy (the VLA) and an Embodiment (a real robot or simulator).

## Guide

- [Quickstart](https://inspectrobots.org/guide/quickstart/)
- [Concepts](https://inspectrobots.org/guide/concepts/)
- [Writing a benchmark](https://inspectrobots.org/guide/writing-a-benchmark/)
- [Policies and embodiments](https://inspectrobots.org/guide/policies-and-embodiments/)
- [Scoring](https://inspectrobots.org/guide/scoring/)
- [Logging & Rerun](https://inspectrobots.org/guide/logging-and-rerun/)
- [Plugins & the registry](https://inspectrobots.org/guide/plugins/)
- [Authoring an embodiment adapter](https://inspectrobots.org/guide/adapters/)
- [Command-line interface](https://inspectrobots.org/guide/cli/)