Skip to content
Change the repository type filter

All

    Repositories list

    • inspect-action

      Public
      Running UK AISI's Inspect in the Cloud
      Python
      593710Updated Jan 3, 2026Jan 3, 2026
    • Python
      5100Updated Jan 3, 2026Jan 3, 2026
    • Bridge for inspect <> verifiers.
      Python
      0000Updated Jan 3, 2026Jan 3, 2026
    • inspect-agents

      Public
      METR's wrapper around the inspect react agent. Intended to allow consistent usage and customization.
      Python
      1440Updated Jan 2, 2026Jan 2, 2026
    • inspect_ai

      Public
      Inspect: A framework for large language model evaluations
      Python
      363410Updated Jan 2, 2026Jan 2, 2026
    • Build docker containers using docker build cloud without a docker daemon
      HCL
      0100Updated Jan 2, 2026Jan 2, 2026
    • A Kubernetes sandbox environment for use with inspect_ai
      Python
      15200Updated Jan 2, 2026Jan 2, 2026
    • prime-rl

      Public
      Decentralized RL Training at Scale
      Python
      168000Updated Jan 1, 2026Jan 1, 2026
    • Modelscan but in Inspect
      Python
      0202Updated Dec 15, 2025Dec 15, 2025
    • Python
      1180Updated Dec 11, 2025Dec 11, 2025
    • Python
      54123Updated Dec 10, 2025Dec 10, 2025
    • Estimate the time horizon of AIs over time on various domains like knowledge and vision
      Python
      0400Updated Dec 3, 2025Dec 3, 2025
    • SCSS
      4301Updated Nov 20, 2025Nov 20, 2025
    • HTML
      31820Updated Nov 19, 2025Nov 19, 2025
    • HTML
      1711312Updated Nov 19, 2025Nov 19, 2025
    • Software Engineering Agents for Inspect AI
      Python
      9100Updated Nov 11, 2025Nov 11, 2025
    • vivaria

      Public
      Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
      TypeScript
      391282186Updated Nov 11, 2025Nov 11, 2025
    • Python
      11140Updated Nov 6, 2025Nov 6, 2025
    • Python
      1000Updated Nov 5, 2025Nov 5, 2025
    • .github

      Public
      0000Updated Nov 5, 2025Nov 5, 2025
    • Python
      0000Updated Nov 5, 2025Nov 5, 2025
    • RE-Bench

      Public
      Python
      1712750Updated Oct 16, 2025Oct 16, 2025
    • Go package to make lightweight ASCII line graph ╭┈╯ in command line apps with no other dependencies.
      Go
      109000Updated Oct 14, 2025Oct 14, 2025
    • Python
      1130Updated Oct 6, 2025Oct 6, 2025
    • Docker image for Spacelift containing Tailscale
      Shell
      7000Updated Sep 26, 2025Sep 26, 2025
    • Python
      0010Updated Sep 23, 2025Sep 23, 2025
    • Python
      0211Updated Sep 12, 2025Sep 12, 2025
    • Some data on SWE-Bench diffs, for labeling.
      0000Updated Sep 3, 2025Sep 3, 2025
    • Terraform module, which takes care of a lot of AWS Lambda/serverless tasks (build dependencies, packages, updates, deployments) in countless combinations 🇺🇦
      HCL
      750000Updated Aug 31, 2025Aug 31, 2025
    • Python
      0000Updated Aug 2, 2025Aug 2, 2025