CalibratedDecisions.

Repo · Safety & guardrails

Edward

Supervisor for unattended coding agents (CI, overnight runs) that wraps any subprocess with deterministic rules and an optional advisory scorer;…

Open github.com ↗

From the repository

The supervisor for coding agents that run when nobody's watching — deterministic guardrails + local semantic scorer + resumable interventions, every decision signed.

agent-safetyai-agentscost-controlguardrailsllmpython

How builders describe it

Supervisor for unattended coding agents (CI, overnight runs) that wraps any subprocess with deterministic rules and an optional advisory scorer; EDWARD_SCORER_BACKEND=jev batches all probes into one TypeSafe Jev call per check.
Supervisor for unattended coding agents: it tracks cross-turn state and asks one batched Jev Choice whether a trajectory should continue, pause or escalate, while deterministic code owns dangerous-command blocking, budget caps and Ed25519-signed receipts.

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