Observability & evals

Agent observability platform for tracing, evaluating, monitoring and improving AI agents

AI governance platform to discover, test, monitor and govern AI systems and enforce controls

Collaboration layer for AI engineering teams: prompt management, agent observability and evals

Monitor the performance, usage, cost and guardrails of LLM and agentic AI apps in Elastic Observability

Open-source workspace where teams build AI agents by chatting and run them in Slack, WhatsApp or Telegram

AI security platform covering discovery, assessment, runtime protection and governance of AI apps and agents

Enterprise agent security and governance platform covering agent discovery, guardrails, evals and traces

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

Meta's open classifier models that detect prompt injection and jailbreak attacks on LLM inputs.

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

Discovers, tests, secures and governs every AI agent in an organization from one platform.

Platform for agent observability and evals: trace agents, score outputs and find patterns in production

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

Open-source holistic solution for AI and ML validation: testing, CI and monitoring

IBM model family that judges whether LLM inputs and outputs meet criteria such as jailbreak, harm and hallucination checks.

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

Microsoft AI service that detects harmful text and image content and screens user input for prompt attacks.