Ai Red Team Python Packages

giskard

🐢 Open-Source Evaluation & Testing library for LLM Agents

aptl-labs

Single-user OpenRÆ backend for creating sandboxes, cyber ranges, digital twins, and other environments.

hermes-jailbench

Zero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench

agent-action-guard

🛡️ Safe AI Agents through Action Classifier

agentic-security

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

aisploit

🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.

scbe-aethermoore

Geometric AI governance and evaluation framework with a 14-layer security pipeline, semantic projection, and reproducible benchmark lanes.

sentinel-llm-security

Open-source AI security lab: EN/RU academy, public Rust defenses, research and local input evaluation. Explore Spectorn for live protection.

rlm-toolkit

Open-source AI security lab: EN/RU academy, public Rust defenses, research and local input evaluation. Explore Spectorn for live protection.

agentprobe-injection

Defense evaluation harness for LLM agents — measure resistance to indirect prompt injection and compare defense effectiveness (delimiter, sandwich, screening, etc.)

mseep-agentic-security

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

scbe-agent-bus

Geometric AI governance and evaluation framework with a 14-layer security pipeline, semantic projection, and reproducible benchmark lanes.

hermes-jailbreak-bench

Zero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench

scbe-bookforge

Geometric AI governance and evaluation framework with a 14-layer security pipeline, semantic projection, and reproducible benchmark lanes.

langalf

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

voigt-kampff

The SAPIEN Framework — an open standard (CC BY 4.0) for measuring AI behavioral safety (sycophantic drift), plus voigt-kampff, the FSL scoring CLI.

scbe-polly-pad

Geometric AI governance and evaluation framework with a 14-layer security pipeline, semantic projection, and reproducible benchmark lanes.

scbe-govern

Geometric AI governance and evaluation framework with a 14-layer security pipeline, semantic projection, and reproducible benchmark lanes.