CalibratedDecisions.

Repo · Safety & guardrails

guardrails-md

Berget AI plugin for opencode, pi and Claude Code (plus a git pre-commit hook) that scores every bash command with a System One decision model…

Open github.com ↗

From the repository

opencode plugin: a System One decision model judges every bash command before it runs — destructive / credentials / your guardrails.md policy

ai-safetyguardrailsopencodeopencode-pluginsystemone

How builders describe it

Berget AI plugin for opencode, pi and Claude Code (plus a git pre-commit hook) that scores every bash command with a System One decision model against your repo's guardrails.md before it runs; defaults to Berget's berget/bev model, and any /v1/systemone-compatible endpoint (TypeSafe settings as…

The decision Jev makes

Allow, flag or escalate a message, tool call or action.

Where it fits

Screening messages, tool calls and outputs before they cause trouble. Jev gives a fast, calibrated verdict that can sit in front of every request or agent action. All 229 safety & guardrails projects →

Related projects