OpenBox AI and Mastra Add Default Runtime Governance to TypeScript Agents

May 5, 2026
OpenBox AI and Mastra have partnered to integrate runtime governance directly into the Mastra TypeScript agent framework, enabling compliance-ready oversight and audit capabilities by default.

OpenBox AI and Mastra have partnered to make runtime governance a built-in feature for all TypeScript agents built on the Mastra framework, announced in a press release.

The integration introduces automatic oversight for every tool invocation, workflow step, and inter-agent message within Mastra. Each action is scored using the OWASP AI Vulnerability Scoring System and classified into one of five verdicts: allow, constrain, require approval, block, or halt. Verdicts are returned in under 250 milliseconds under normal workloads, and all actions are cryptographically attested and logged.

The system also supports human-in-the-loop approvals that persist across restarts and includes built-in detection for personally identifiable information and content moderation. Enterprises can access compliance-ready dashboards and governance for multi-agent workflows, with new tools automatically covered as applications grow.

The integration is available now for all Mastra developers, with documentation and a free tier accessible at openbox.ai.

We hope you enjoyed this article

Free newsletter

Cybersecurity AI Weekly

Weekly newsletter about AI in Cybersecurity.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.