Model Evaluation and Threat Research (METR)

METR is a research nonprofit that works on assessing whether cutting-edge AI systems could pose catastrophic risks to society.

We build the science of accurately assessing risks, so that humanity is informed before developing transformative AI systems.

Our Software

Inspect AI Cloud Platform
Public Task Suite
RE-Bench Task Suite
Some of our open-source agents can be found at github.com/poking-agents
Vivaria (deprecated)

Pinned Loading

hawk hawk Public

Run Inspect AI evals in the cloud

Python 109 64

Repositories

Type

All Public Sources Forks Archived Mirrors Templates

Language

All C C++ Go HCL HTML Python SCSS Shell Swift TypeScript

Sort

Last updated Name Stars

Showing 10 of 69 repositories

hawk Public
Run Inspect AI evals in the cloud

METR/hawk's past year of commit activity

Python 109 MIT 64 198 235 Updated Nov 12, 2026
inspect_ai Public Forked from UKGovernmentBEIS/inspect_ai
Inspect: A framework for large language model evaluations

METR/inspect_ai's past year of commit activity

Python 11 MIT 929 0 3 Updated Nov 12, 2026
inspect_k8s_sandbox Public Forked from UKGovernmentBEIS/inspect_k8s_sandbox
A Kubernetes sandbox environment for use with inspect_ai

METR/inspect_k8s_sandbox's past year of commit activity

Python 3 MIT 42 0 0 Updated Nov 12, 2026
inspect-test-utils Public
Utilities for testing Inspect AI

METR/inspect-test-utils's past year of commit activity

Python 1 MIT 4 0 1 Updated Nov 11, 2026
inspect-agents Public
A collection of METR wrappers around Inspect agents and of METR scanners for Inspect Scout. Intended to allow consistent usage and customization.

METR/inspect-agents's past year of commit activity

Python 11 MIT 7 3 35 Updated Nov 11, 2026
inspect-metr-task-bridge Public

METR/inspect-metr-task-bridge's past year of commit activity

Python 1 2 1 4 Updated Nov 11, 2026
inspect_scout Public Forked from meridianlabs-ai/inspect_scout

METR/inspect_scout's past year of commit activity

Python 1 MIT 62 0 2 Updated Nov 6, 2026
activitywatch Public Forked from ActivityWatch/activitywatch
The best free and open-source automated time tracker. Cross-platform, extensible, privacy-focused.

METR/activitywatch's past year of commit activity

Python 0 MPL-2.0 1,107 0 0 Updated Nov 5, 2026
terraform-provider-aws Public Forked from hashicorp/terraform-provider-aws
The AWS Provider enables Terraform to manage AWS resources.

METR/terraform-provider-aws's past year of commit activity

Go 0 MPL-2.0 10,636 0 0 Updated Oct 30, 2026
inspect-eval-utils Public

METR/inspect-eval-utils's past year of commit activity

Python 0 MIT 0 0 0 Updated Oct 30, 2026

View all repositories

People

Top languages

Python TypeScript Go HCL Shell

Most used topics

evals ai ai-evaluation elicitation llm