Repositories list

• harbor-trajectories

  Public
  HTML

  •0•0•0•0•Updated Feb 14, 2026Feb 14, 2026

• harbor-mm

  Public
  Harbor is a framework for running agent evaluations and creating and using RL environments.

  Python

  •

  Apache License 2.0

  •443•0•0•3•Updated Feb 12, 2026Feb 12, 2026

• gauntlet-analytics

  Public
  Stratified sampling of the Gauntlet dataset for SFT

  0•0•0•0•Updated Feb 12, 2026Feb 12, 2026

• terminal-bench-3

  Public
  0•0•0•0•Updated Feb 12, 2026Feb 12, 2026

• web-eval-agent

  Public
  An MCP server that autonomously evaluates web applications.

  debuggingqamcp+ 6debugging-toolplaywrightmcp-servermodelcontextprotocolvibe-codingvibe-testing

  Python

  •

  Apache License 2.0

  •106•1.2k•0•15•Updated Feb 11, 2026Feb 11, 2026

• harbor-cua

  Public
  Harbor is a framework for running agent evaluations and creating and using RL environments.

  Python

  •

  Apache License 2.0

  •443•0•0•0•Updated Feb 8, 2026Feb 8, 2026

• harbor-refresh-task-contributions

  Public
  Harbor is a framework for running agent evaluations and creating and using RL environments.

  Python

  •

  Apache License 2.0

  •443•0•0•1•Updated Jan 30, 2026Jan 30, 2026

• ledgit

  Public
  Python

  •0•0•0•0•Updated Jan 30, 2026Jan 30, 2026

• .github

  Public
  MIT License

  •0•0•0•0•Updated Jan 26, 2026Jan 26, 2026

• AutoRLEnv

  Public
  Automatic RL Environments. (ARLE)

  Python

  •0•1•0•0•Updated Dec 12, 2025Dec 12, 2025

• scale-agentex

  Public
  Open source codebase for Scale Agentex

  Python

  •

  Apache License 2.0

  •30•0•0•0•Updated Nov 12, 2025Nov 12, 2025

• refresh-context-engine

  Public
  TypeScript

  •

  MIT License

  •1•3•0•0•Updated Oct 21, 2025Oct 21, 2025

• demo

  Public template
  🤖 Fork me to try out Dependabot

  Ruby

  •4.3k•0•0•0•Updated Jul 21, 2025Jul 21, 2025