“Python”

Open-source Python framework from Microsoft for finding risks in generative AI systems through red teaming.

Open-source Python library for adding programmable guardrails to LLM-based conversational applications

Python tool that scans MCP servers and their tools for security findings using YARA, LLM and AI Defense analysis.

Python framework with input and output guards that detect LLM risks, plus structured output generation

Open-source Python library for evals, red teaming and test generation for agentic systems

Open-source observability for LLM applications, built on OpenTelemetry

Continuous-improvement stack for agents: monitor behavior, detect failures and validate fixes

Observability and dev-tool platform for building, evaluating and monitoring AI agents

Open-source observability for AI apps: traces LLM calls, prompts, retrieval and agent steps via OpenTelemetry

Open-source framework to evaluate, test and monitor ML and LLM systems

Tracing, evaluation and monitoring for LLM apps and agents, with SDKs for several languages