Skip to content
@refreshdotdev

Refresh

Data to augment the future of work
README.md

Welcome to Refresh

Banner

We're building coding and computer use RL environments.

Popular repositories Loading

  1. web-eval-agent web-eval-agent Public

    An MCP server that autonomously evaluates web applications.

    Python 1.2k 105

  2. refresh-context-engine refresh-context-engine Public

    TypeScript 3 1

  3. AutoRLEnv AutoRLEnv Public

    Automatic RL Environments. (ARLE)

    Python 1

  4. demo demo Public template

    Forked from dependabot/demo

    🤖 Fork me to try out Dependabot

    Ruby

  5. scale-agentex scale-agentex Public

    Forked from scaleapi/scale-agentex

    Open source codebase for Scale Agentex

    Python

  6. .github .github Public

Repositories

Showing 10 of 16 repositories
  • taskhunt-api Public

    Backend API for TaskHunt.ai - Terminal Bench Task Explorer

    refreshdotdev/taskhunt-api’s past year of commit activity
    Python 0 0 0 0 Updated Feb 17, 2026
  • taskhunt-web Public

    Frontend for TaskHunt.ai - Terminal Bench Task Explorer

    refreshdotdev/taskhunt-web’s past year of commit activity
    TypeScript 0 0 0 0 Updated Feb 17, 2026
  • taskhunt.ai Public

    Explore and visualize terminal bench tasks across all benchmarks

    refreshdotdev/taskhunt.ai’s past year of commit activity
    0 0 0 0 Updated Feb 17, 2026
  • harbor-trajectories Public
    refreshdotdev/harbor-trajectories’s past year of commit activity
    Shell 0 0 0 0 Updated Feb 17, 2026
  • harbor-mm Public Forked from laude-institute/harbor

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

    refreshdotdev/harbor-mm’s past year of commit activity
    Python 0 Apache-2.0 480 0 3 Updated Feb 12, 2026
  • gauntlet-analytics Public

    Stratified sampling of the Gauntlet dataset for SFT

    refreshdotdev/gauntlet-analytics’s past year of commit activity
    0 0 0 0 Updated Feb 12, 2026
  • terminal-bench-3 Public
    refreshdotdev/terminal-bench-3’s past year of commit activity
    0 0 0 0 Updated Feb 12, 2026
  • web-eval-agent Public

    An MCP server that autonomously evaluates web applications.

    refreshdotdev/web-eval-agent’s past year of commit activity
    Python 1,235 Apache-2.0 105 0 15 Updated Feb 11, 2026
  • harbor-cua Public Forked from laude-institute/harbor

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

    refreshdotdev/harbor-cua’s past year of commit activity
    Python 0 Apache-2.0 480 0 0 Updated Feb 8, 2026
  • harbor-refresh-task-contributions Public Forked from laude-institute/harbor

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

    refreshdotdev/harbor-refresh-task-contributions’s past year of commit activity
    Python 0 Apache-2.0 480 0 1 Updated Jan 30, 2026
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

Loading…