← Trending

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

HarmBench

github.com

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

LibraryOpen source

Visit github.comexternal siteGitHub1,119 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. Automated red teaming for your LLM app

    and seeing all the bad things people did.

    Hacker News23 ptspromptfoo.devlatest reaction

  2. T3MP3ST

    autonomous red teaming platform; multi-agent offensive-security meta-harness

    GitHub7,004 starsgithub.comOpen sourcelatest reaction

  3. safelabs-eval

    Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy

    GitHub814 starsgithub.comLibraryOpen sourcelatest reaction

  4. rogue

    AI Agent Evaluator & Red Team Platform

    GitHub1,075 starsgithub.comOpen sourcelatest reaction

  5. agentic_security

    Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

    GitHub2,043 starsgithub.comOpen sourcelatest reaction