Repo · Coding & code review
Canny
A warden that will not let a coding agent finish on a claim.
Open github.com ↗How builders describe it
Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.
Warden for Claude Code and Codex CLI: an append-only session ledger and deterministic “done” gate, with optional TypeSafe Jev judgments that advise but never alone block.
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 227 coding & code review projects →
Related projects
Coding & code reviewVejA Jev clone that runs locally, built with Claude in a night.GitHub · Daniel Raeder
Coding & code reviewstingrayA Claude Code Stop hook for the turn that ends half-done — nothing done, an announced action never carried out, a promise to watch CI with nothing…GitHub · ★ 5 · Nanako0129
Coding & code reviewjev-enforce📏 Claude Code plugin that makes Claude follow your CLAUDE.md: every reply and edit checked by TypeSafe Jev ✅.GitHub · ★ 4 · erkamyaman
Coding & code reviewwellposedZero-dependency linter for TypeSafe Jev requests: catches broken state paths, missing Choice escape hatches, bundled judgments, and other structural…GitHub · ★ 2 · suraj-phanindra
Coding & code reviewjev-claude-codePrompt Claude Code: tre sistemi costruiti su Jev di TypeSafe — routing del modello, compattazione del contesto e code review.GitHub · ★ 2 · DarioFontanel
Coding & code reviewjev-starter (YanfLIZi56)Visually configure Jev questions, test them live, export ready-to-use code.GitHub · ★ 2 · YanfLIZi56