CalibratedDecisions.

Repo · Coding & code review

adecider

Typed System One decisions for coding agents: one call sends state plus many Noul/Choice/Score questions and returns calibrated answers; backends are…

Open github.com ↗

From the repository

Typed System One decisions for any coding agent: one call, many typed questions, calibrated probabilities instead of prose, pluggable backends (local Laya, TypeSafe Jev, any OpenAI-compatible)

How builders describe it

Typed System One decisions for coding agents: one call sends state plus many Noul/Choice/Score questions and returns calibrated answers; backends are pluggable (local Laya by default, TypeSafe Jev, or OpenAI-compatible escape hatch).

The decision Jev makes

Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.

Where it fits

Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 239 coding & code review projects →

Related projects