AIX360

LangDB is an AI agent observability tool for debugging and optimizing AI workflows. It provides real-time monitoring, tracing, and analytics across various frameworks like LangChain, Google ADK, and OpenAI. LangDB offers comprehensive observability for AI agents, enabling users to trace, analyze, and optimize their performance.

power-pwn is an open-source security toolset designed for offensive and defensive security measures. It facilitates the discovery, reconnaissance, and ethical assessment of AI agents. The tool helps security professionals and AI developers identify and address potential vulnerabilities in AI systems. It is available on GitHub.

adversarial-attacks-pytorch is a PyTorch library that provides adversarial attacks for generating adversarial examples. It offers a PyTorch-like interface to simplify the implementation of these attacks. The library is designed to help PyTorch users test and improve the robustness of their models against adversarial threats.

Guardrails is an open-source toolkit for adding programmable guardrails to LLM-based conversational systems. It allows developers to easily implement safety measures and control the behavior of LLMs. The tool helps ensure that conversational AI systems are safe, reliable, and aligned with desired policies.

judgeval is an open-source tool designed for agent behavior monitoring. It facilitates tracking and judging agent behavior in both online and offline environments. The tool enables users to set up alerts and analyze agent behaviors and topic patterns at scale. judgeval supports agent post-training and monitoring.

agent-scan is a security scanner for AI agents, MCP servers, and agent skills. It helps discover and scan agent components for prompt injections and vulnerabilities. The tool supports scanning agent skills and helps maintain an inventory of agent components.