Hawk

Framework / harness (not an eval — tooling/reference entry)

METR's open-source platform for running agent evals at scale on Inspect.

Category: Eval frameworks & harnesses
Insurance exposure: Unmapped
Publisher: METR
Publisher type: Nonprofit / research org
License: MIT
Status: Active (<90d)
Last commit: 2026-10-15
Stars: 94
Notes: Successor to Vivaria.

View source on GitHub →

Wanich Risk Lab, 2026.