Inspect AI
MIT LLM and agent evaluation framework from the UK AI Security Institute
AI Agents / Agents · OSS/MIT · 3k
Reviewed 2026-10-20 · last push 2026-10-19 · repo checked 2026-10-20
What's Good
MIT (UKGovernmentBEIS/inspect_ai), release 0.3.282 (2026-10-19). ★~3.0k (~19 a week). Useful when you need repeatable evals of models or agents that use tools, and want to inspect each run afterwards.
The Catch
It is still 0.x and releases near-daily, so pin a version or your eval results can shift under you.
Verdict
A serious, actively developed eval framework; pin it.
Embed
Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.
Markdown
[](https://stackgems.com/gems/inspect-ai)
HTML
<a href="https://stackgems.com/gems/inspect-ai"><img src="https://stackgems.com/badge/inspect-ai.svg" alt="Inspect AI reviewed on Stack Gems" height="20"></a>
Related
AI Agents →- Arize PhoenixELv2 self-host AI observability & eval — traces, datasets, playground
- e2e (TesterArmy)Apache-2.0 agent-driven e2e tests for web and mobile — replays without model calls
- OpikApache-2.0 LLM and agent tracing, evaluation and monitoring by Comet
- LangWatchApache-2.0 LLM tracing, agent tests, evals, gateway
- HolmesGPTApache-2.0 CNCF AI agent for production incidents