Arcjet launches runtime security to track and control AI agents in production

Startup Arcjet Labs introduced agent runtime security, a service that tracks AI agent actions in production and checks each step against policies before execution. Integration is via OpenTelemetry or Anthropic's Compliance API without code changes; Open Policy Agent policies change without redeployment.

• Each agent action is checked against policy before execution and logged
• Integrations with Claude Agent SDK, OpenAI Agents SDK, LangChain, Mastra and Agent Framework
• Open Policy Agent rules change without redeploying the application
• Python and Go SDKs updated to version 1.0; software used by 500+ applications