← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

terminal-bench

github.com

Measuring and evolving with the frontier of agent work

LibraryOpen source

Visit github.comexternal siteGitHub1,018 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. harbor

    Framework for evaluating and improving agents

    github.comLibraryOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    6,875 stars

  2. harness

    A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    9,335 stars

  3. harvey-labs

    A benchmark built to evaluate and improve agent capabilities for supporting legal work.

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    1,576 stars

  4. Skill-up

    Regression testing for Agent Skills

    github.comOpen source2 reactionslatest reaction

    Hacker News
    5 pts
    GitHub
    1,438 stars

  5. Sage

    An RSI Agent Harness for running, evaluating, and evolving agents—with tools, skills, MCP, stateful execution, and multi-agent workflows.

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    1,211 stars