CalibratedDecisions.

Repo · SDKs & integrations

openclaw-typesafe-ai

OpenClaw plugin that registers one optional agent tool, typesafe_decide, for explicit TypeSafe Jev decisions over caller-supplied state—no hooks,…

Open github.com ↗

From the repository

Optional typed TypeSafe AI Jev decisions for OpenClaw, with SecretRef credentials and strict API validation.

How builders describe it

OpenClaw plugin that registers one optional agent tool, typesafe_decide, for explicit TypeSafe Jev decisions over caller-supplied state—no hooks, model provider, or ambient conversation capture. Independent of the broader hook-based community OpenClaw TypeSafe plugin.
An OpenClaw plugin that registers a single optional tool, typesafe_decide, forwarding caller-supplied text or JSON state plus typed noul, choice and score questions to the System One endpoint, with jev-latest as the default model.

The decision Jev makes

Any Jev question: yes or no, a choice, or a score, from your own stack.

Where it fits

Official and community SDKs, MCP servers and integrations for calling Jev from the languages and tools you already use. All 625 sdks & integrations projects →

Related projects