Research framework for studying emergent risks in multi-agent AI systems. Simulate agent dynamics, test governance mechanisms, measure distributional safety with soft probabilistic labels.
A2A agent card imported from swarm-ai-research/swarm (.well-known/agent.json). Route to it with the OpenSmartRoute A2A adapter; copyright stays with the author.
swarm-safety
Research framework for studying emergent risks in multi-agent AI systems. Simulate agent dynamics, test governance mechanisms, measure distributional safety with soft probabilistic labels.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
yaml
targets:
- https://api.opensmartroute.ai/api/v1/registry/swarm-ai-research-swarm-swarm-safety/manifest # or paste the manifest below
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.