Skip to content
Change the repository type filter

All

    Repositories list

    • SCSS
      MIT License
      4302Updated May 1, 2026May 1, 2026
    • hawk

      Public
      Run Inspect AI evals in the cloud
      PLpgSQL
      312030Updated May 1, 2026May 1, 2026
    • Inspect: A framework for large language model evaluations
      Python
      MIT License
      480502Updated May 1, 2026May 1, 2026
    • ts-mono

      Public
      TypeScript monorepo
      TypeScript
      7000Updated May 1, 2026May 1, 2026
    • macOS GUI to view large inspect samples. Integrated with Hawk
      Swift
      0000Updated May 1, 2026May 1, 2026
    • A collection of METR wrappers around Inspect agents and of METR scanners for Inspect Scout. Intended to allow consistent usage and customization.
      Python
      1648Updated Apr 30, 2026Apr 30, 2026
    • Python
      MIT License
      18100Updated Apr 27, 2026Apr 27, 2026
    • Python
      1142Updated Apr 16, 2026Apr 16, 2026
    • A Kubernetes sandbox environment for use with inspect_ai
      Python
      MIT License
      20200Updated Apr 14, 2026Apr 14, 2026
    • Python
      Other
      8495Updated Apr 14, 2026Apr 14, 2026
    • Python
      0460Updated Apr 11, 2026Apr 11, 2026
    • Running UK AISI's Inspect in the Cloud
      Python
      MIT License
      11000Updated Apr 10, 2026Apr 10, 2026
    • Running UK AISI's Inspect in the Cloud
      Python
      MIT License
      1124199Updated Apr 6, 2026Apr 6, 2026
    • Inspect tasks <> Tinker RL envs
      Python
      MIT License
      2700Updated Mar 10, 2026Mar 10, 2026
    • Public repository containing METR's DVC pipeline for eval data analysis
      Python
      4927494Updated Mar 6, 2026Mar 6, 2026
    • Python
      1401Updated Feb 24, 2026Feb 24, 2026
    • 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
      21501Updated Feb 23, 2026Feb 23, 2026
    • Post-training with Tinker
      Python
      Apache License 2.0
      406001Updated Feb 18, 2026Feb 18, 2026
    • vivaria

      Public
      Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
      TypeScript
      MIT License
      371362185Updated Feb 15, 2026Feb 15, 2026
    • HCL
      Apache License 2.0
      30000Updated Feb 6, 2026Feb 6, 2026
    • Datadog MCP Server - Comprehensive monitoring and observability tools for Datadog via Model Context Protocol
      Python
      22000Updated Jan 30, 2026Jan 30, 2026
    • Modelscan but in Inspect
      Python
      0201Updated Jan 20, 2026Jan 20, 2026
    • prime-rl

      Public
      Decentralized RL Training at Scale
      Python
      Apache License 2.0
      279000Updated Jan 20, 2026Jan 20, 2026
    • HTML
      Other
      42021Updated Jan 19, 2026Jan 19, 2026
    • HTML
      Other
      1912112Updated Jan 19, 2026Jan 19, 2026
    • Python
      0010Updated Jan 7, 2026Jan 7, 2026
    • Bridge for inspect <> verifiers.
      Python
      MIT License
      0000Updated Jan 7, 2026Jan 7, 2026
    • Build docker containers using docker build cloud without a docker daemon
      HCL
      MIT License
      0100Updated Jan 2, 2026Jan 2, 2026
    • Estimate the time horizon of AIs over time on various domains like knowledge and vision
      Python
      2500Updated Dec 3, 2025Dec 3, 2025
    • Software Engineering Agents for Inspect AI
      Python
      MIT License
      25100Updated Nov 11, 2025Nov 11, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.