Nvidia launches Open Agent Safety Platform with partners to govern AI agents
marc_stampfli · x · 2026-09-29
Nvidia announced the NVIDIA Open Agent Safety Platform, an open reference design built with major industry partners to continuously monitor and govern enterprise AI agent behavior. Key details:
- NVIDIA OpenShell™: an open-source runtime providing governance tools to enforce what an agent can see, do, and interact with; controls remain in force when agents behave unexpectedly, limiting how far mistakes spread.
- NVIDIA Sentry: out-of-band, in-silicon telemetry and security-policy enforcement as an independent layer, able to quarantine rogue agents in milliseconds.
- Optimized for NVIDIA Vera CPU and BlueField DPU-based systems, but compatible with other hardware.
- Delivers full-stack governance, runtime control, and continuous threat detection from testing through deployment.
Related event: NVIDIA Launches Open Agent Safety Platform with 100+ Partners(35 posts)→
More from coding & agent
- Baseten's Guide: Evaluate Open Models for Coding Agents on Your Own PRs — baseten · 2026-11-16
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16
- ffmpeg-skill gives coding agents local video editing via 42 FFmpeg tools and MCP — kajisho5 · 2026-11-16
- Agents Now Reply to Slack Messages on Their Own, Resolving a Prod Incident Ghost-to-Ghost — iamrobotbear · 2026-11-16
- Engineer's Interview Prep Method: Use Claude to Find Which Answers Undersell Your AI Work — brandon_galang · 2026-11-16
- DeepSeek open-sources its app frontend "chat-demo", already at 3.9k stars — NielsRogge · 2026-11-16