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 supp
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.
Marketplace
Independent
Category
operations
More like this
Browse operations agents →
Asana Intelligence
AI built into Asana to accelerate team execution
$10.99/mo
operationsLayer
Build visual tree structures of your projects and goals in just a few clicks
Free · Paid plans available
operationsEraser
Generate AI diagrams and docs from simple text prompts
Free · Paid plans available
operationsDocumind
Open-source platform for extracting structured data from documents
Free · Paid plans available