jevbooks

← All projects

stanley-code

devagrawal09/stanley-code

Bounded TypeSafe Jev workflows for coding agents.

Classification & Routing43%Runner-up: Agent Decisions

What it is

Stanley is a command-line tool for checking and understanding code changes. You describe what you need in natural language; it routes the request to one bounded workflow that gathers evidence and asks Jev fixed-choice questions.

How it uses Jev

Jev routes a natural-language request across workflows using author-provided JSON routing metadata plus deterministic facts. For built-ins, Jev answers fixed-choice questions about small, size-limited pieces of the diff or evidence; Stanley's own code turns answers into flags using fixed thresholds.

Primitives:choice

Technique worth stealing

Deterministic code gathers bounded evidence and asks Jev small fixed-choice questions; code, not the model, makes decisions.

Try it

Build from source: git clone, npm ci, npm run build, then node dist/cli.js --help.

View on GitHub

judged by Jevjev-1.13.0

Evidence

Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.

  • Jev-centricyes0.83
  • Shows a System One patternyes0.87
  • Handles uncertaintyyes0.77
  • Measuredno0.04
  • Runnableyes0.93
  • Worth recommendingunclear0.47
  • Model replicano0.06
  • Problem scopescore on a 0–2 scale1.95
  • About Jevyes0.98

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.