agent-safe-pipeline
Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.
About
An execution-authority gateway for AI agents and APIs. It intercepts consequential HTTP actions, asks Decionis whether they are authorized, and forwards exactly the authorized request once on a single-use grant, holds it for a person, or refuses it, leaving chained evidence of each. Installs by Homebrew, Linux package, Docker or Helm.
Languages
Contributors4
![decionis-bot[bot]](https://avatars.githubusercontent.com/u/289489188?v=4)
![dependabot[bot]](https://avatars.githubusercontent.com/in/29110?v=4)
No features listed.
Comments Theme
