Skip to content

@METR METR

Change the repository type filter

All

    Repositories list

    59 repositories

    • evaluation-resources

      Public
      SCSS
      •
      MIT License
      •4•3•0•3•Updated Apr 30, 2026Apr 30, 2026

    • hawk

      Public
      Run Inspect AI evals in the cloud
      awsllmevals
      awsllmevalsinspect-ai
      PLpgSQL
      •3•11•0•34•Updated Apr 29, 2026Apr 29, 2026

    • ts-mono

      Public
      TypeScript monorepo
      TypeScript
      •7•0•0•0•Updated Apr 29, 2026Apr 29, 2026

    • inspect_ai

      Public
      Inspect: A framework for large language model evaluations
      Python
      •
      MIT License
      •475•5•0•2•Updated Apr 28, 2026Apr 28, 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.
      Python
      •1•6•4•7•Updated Apr 28, 2026Apr 28, 2026

    • inspect_scout

      Public
      Python
      •
      MIT License
      •18•1•0•0•Updated Apr 27, 2026Apr 27, 2026

    • inspect-eagle

      Public
      macOS GUI to view large inspect samples. Integrated with Hawk
      Swift
      •0•0•0•0•Updated Apr 22, 2026Apr 22, 2026

    • inspect-metr-task-bridge

      Public
      Python
      •1•1•4•2•Updated Apr 16, 2026Apr 16, 2026

    • inspect_k8s_sandbox

      Public
      A Kubernetes sandbox environment for use with inspect_ai
      Python
      •
      MIT License
      •20•2•0•0•Updated Apr 14, 2026Apr 14, 2026

    • inspect-tasks-public

      Public
      Python
      •
      Other
      •8•4•9•5•Updated Apr 14, 2026Apr 14, 2026

    • triframe_inspect

      Public
      Python
      •0•4•6•0•Updated Apr 11, 2026Apr 11, 2026

    • inspect-action-jonathan

      Public
      Running UK AISI's Inspect in the Cloud
      Python
      •
      MIT License
      •11•0•0•0•Updated Apr 10, 2026Apr 10, 2026

    • inspect-action

      Public
      Running UK AISI's Inspect in the Cloud
      aiinspectelicitation
      aiinspectelicitationai-evaluationevals
      Python
      •
      MIT License
      •11•24•19•12•Updated Apr 6, 2026Apr 6, 2026

    • inspect-tinker-bridge

      Public
      Inspect tasks <> Tinker RL envs
      Python
      •
      MIT License
      •2•7•0•0•Updated Mar 10, 2026Mar 10, 2026

    • eval-analysis-public

      Public
      Public repository containing METR's DVC pipeline for eval data analysis
      Python
      •49•270•9•4•Updated Mar 6, 2026Mar 6, 2026

    • Measuring-Late-2025-AI-on-OSS-Devs

      Public
      Python
      •1•4•0•1•Updated Feb 24, 2026Feb 24, 2026

    • Measuring-Early-2025-AI-on-Exp-OSS-Devs

      Public
      Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity: https://metr.org/blog/2025-07-10-early-2025-ai-experienced-os-dev-study…
      Python
      •2•15•0•1•Updated Feb 23, 2026Feb 23, 2026

    • tinker-cookbook

      Public
      Post-training with Tinker
      Python
      •
      Apache License 2.0
      •403•0•0•1•Updated Feb 18, 2026Feb 18, 2026

    • vivaria

      Public
      Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
      aielicitationai-evaluation
      aielicitationai-evaluationevals
      TypeScript
      •
      MIT License
      •37•136•218•5•Updated Feb 15, 2026Feb 15, 2026

    • terraform-aws-iam-identity-center

      Public
      HCL
      •
      Apache License 2.0
      •29•0•0•0•Updated Feb 6, 2026Feb 6, 2026

    • datadog-mcp

      Public
      Datadog MCP Server - Comprehensive monitoring and observability tools for Datadog via Model Context Protocol
      Python
      •22•0•0•0•Updated Jan 30, 2026Jan 30, 2026

    • modelscan-inspect

      Public
      Modelscan but in Inspect
      Python
      •0•2•0•1•Updated Jan 20, 2026Jan 20, 2026

    • prime-rl

      Public
      Decentralized RL Training at Scale
      Python
      •
      Apache License 2.0
      •275•0•0•0•Updated Jan 20, 2026Jan 20, 2026

    • hcast-public

      Public
      HTML
      •
      Other
      •4•20•2•1•Updated Jan 19, 2026Jan 19, 2026

    • public-tasks

      Public
      HTML
      •
      Other
      •19•121•1•2•Updated Jan 19, 2026Jan 19, 2026

    • task-assets

      Public
      Python
      •0•0•1•0•Updated Jan 7, 2026Jan 7, 2026

    • inspect-verifiers-bridge

      Public
      Bridge for inspect <> verifiers.
      Python
      •
      MIT License
      •0•0•0•0•Updated Jan 7, 2026Jan 7, 2026

    • terraform-docker-build

      Public
      Build docker containers using docker build cloud without a docker daemon
      HCL
      •
      MIT License
      •0•1•0•0•Updated Jan 2, 2026Jan 2, 2026

    • cross-domain-horizon

      Public
      Estimate the time horizon of AIs over time on various domains like knowledge and vision
      Python
      •2•5•0•0•Updated Dec 3, 2025Dec 3, 2025

    • inspect_swe

      Public
      Software Engineering Agents for Inspect AI
      Python
      •
      MIT License
      •24•1•0•0•Updated Nov 11, 2025Nov 11, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.