Skip to content
microsoft / SafeAgentsView on GitHub
A unified framework for building and evaluating safe multi-agent systems. Write once, run on Autogen, LangGraph, or OpenAI Agents. Built-in safety evaluation (ARIA, DHARMA), attack detection, and support for benchmarks like AgentHarm and ASB.
☆18Oct 28, 2026Updated 2 weeks ago

Alternatives and similar repositories for SafeAgents

Users that are interested in SafeAgents are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?