inspect_ai

Inspect AI core: composable eval tasks, sandboxes, scorers, and multi-model runs; the framework behind inspect_evals, not just the task bundle.

Stars

3.1k

Adoption surface

complex

Autonomy

headless

Recovery

resumable

License

✅ open-source

Category

Evaluation and benchmarking harnesses

Repository ↗ Example: Inspect tutorial example ↗

Related in Evaluation and benchmarking harnesses

• Agent Lightning
• SWE-bench
• AgentBench
• WebArena
• ClawBench
• WebVoyager

Maintain inspect_ai? Add the badge

Paste this into your README so readers can find the list and see how inspect_ai compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)

Copy