Back to all startups

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.

Discover startups similar to Keydris

MAKO-AI The future of software development
Kachilu Marketing automation without approval loops
FreeDAST BOOSTED Scan your live site for risks and get a clear security grade
Kilo Code Lightning speed autonomous AI coding agent for VS Code
AdKit Run research, launch, and optimize ads with your AI agent
Carly AI Delegate scheduling, email, and CRM tasks to AI agents you control
Nodlume BOOSTED Centralized System-design workspace for React application design
Leefy Plan AI products visually and hand off clean work to Claude Code