AI red teaming & LLM evaluation
Inspect is an open-source LLM evaluation framework from UK AI Security Institute. It is released under the MIT license and is offered as: CLI, Library, Self-hosted.
Best for
Consider instead if
Inspect is the evaluation framework the UK AI Security Institute builds with Meridian Labs, and other security work runs on it: the b3 agent benchmark listed here installs as an Inspect evaluation. A task is a dataset, a solver and a scorer; inspect eval runs it and the log viewer shows every message and score. For security teams the agent features carry the most weight. Inspect can drive external agents such as Claude Code, Codex CLI and Gemini CLI, and it runs untrusted model code in Docker, Kubernetes, Modal, Proxmox or Vagrant sandboxes. It reaches more than 20 model providers. Compared with garak or promptfoo it is a framework first: you choose or write the security evaluations instead of pointing a scanner at an app endpoint. It is MIT licensed, with no fee.
This summary is our own wording of the sourced facts on this page.
Each value links to the page that states it, with the date we checked it.
As documented by the vendor or project. The tag is our label from a controlled vocabulary.
Our editorial model, not a standard. The primary layer follows the category, except for tools whose main documented job is detection and response; other layers rest on a capability the sources document. How the model works.
| Layer | Role | How it applies | Based on |
|---|---|---|---|
| L4 Testing Testing and red teaming | Primary | Attack and evaluate models, apps and agents on purpose, before release and after every change, to find what the other layers miss. | Follows its category, AI red teaming & LLM evaluation |
The risk list is OWASP's (Top 10 for LLM Applications, 2025). The mapping is our analysis, and each row rests on a capability the sources document.
No OWASP LLM risk is mapped to this tool in our analysis.
More in AI red teaming & LLM evaluation, ranked within the category by Coverage Score.
NVIDIA
Probes language models and LLM apps for prompt injection, jailbreaks, data leakage and more.
Best for: Teams that want a free command-line scanner they can point at any model or LLM endpoint before release
Reviewed
Giskard AI
Generates adversarial test suites for LLM agents and RAG apps, runs them and reports failures by threat type.
Best for: Python teams that want a free library to scan an LLM agent or RAG app for prompt injection and harmful output, and to write pass or fail checks for it
Reviewed
OpenAI (Promptfoo)
Runs evals and red team scans against LLM apps from a CLI or CI pipeline and writes a vulnerability report.
Best for: Developer teams that want one open-source CLI for both prompt evals and red teaming, run locally and in CI
Reviewed
Yes. Inspect is released under the MIT license, and the code is on GitHub at UKGovernmentBEIS/inspect_ai.
The Inspect site says it is developed by the UK AI Security Institute and Meridian Labs.
The site gives pip install inspect-ai. The tutorial runs a task file with the inspect eval command and opens a browser log viewer with inspect view. The reference section documents the Python API and every CLI command.
Yes. The site says it can run external agents such as Claude Code, Codex CLI and Gemini CLI, and it runs untrusted model code in sandboxes such as Docker, Kubernetes, Modal, Proxmox and Vagrant. You still write or pick the evaluation that defines what counts as a failure.
Inspect is released under the MIT license.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
Inspect is offered as: CLI, Library, Self-hosted.
Source Source, checked October 21, 2026: inspect.aisi.org.uk (opens in a new tab) Checked
Pricing model for Inspect: Free.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
Latest release of Inspect: October 19, 2026.
Source Source, checked October 21, 2026: api.github.com (opens in a new tab) Checked
We have no commercial relationship with UK AI Security Institute.