Today we are launching Prismor
Production AI agents operate autonomously with all sensitive access but lack the critical visibility of their actions
Prismor is an open-sourced control plane for AI agents which lets you:
- redact secrets so agents dont read them
- secure supply chain package consumption
- skill and mcp scanning for prompt injection
- scan and fix vulnerabilities (safely and validated)
- all agent executions in a local self-serve dashboard
About 3000 developers are already using it and we'd love for you to give it a shot