gnt.ai docs
gnt checks every action your AI agents take against your company's real rules before it runs.
Quickstart
Get a key, connect an agent, and see how a rule gets approved.
Tools & Enforcement
The 5 MCP tools gnt-brain exposes, and how to enforce check_action before acting.
Connect an Agent
claude.ai, Claude Code, a raw MCP client, OpenAI, Hermes, or OpenClaw.
Sources
Pull decision-prose in from the tools your team already uses.
API Reference
The full HTTP API gnt-brain runs on.