Prismor: Open-source runtime control plane for AI agents

Prismor launched as a free, open-source security layer that sits between AI coding agents such as Claude Code, Codex, and Cursor and the actions those agents take, checking each tool call against a policy before it runs. Every call receives one of three verdicts: allow, warn, or block. The runtime control plane targets agents that run shell commands, read and write files, handle credentials, and call outside APIs, often chaining many steps.