Keydris
Control what AI agents can do before they do it
Keydris is an authorization layer for AI agents. It lets you define what an agent is allowed to do and checks that authority before a governed action executes. For example, a coding agent can be allowed to inspect a repository, require approval for a sensitive action, and be blocked from a prohibited action. Every governed action resolves to ALLOW, APPROVAL REQUIRED, or REJECT. Keydris works with agent workflows including Claude Code, Codex, MCP, GitHub, Slack, and supported local commands.