Did the code satisfy the spec?

Byspec takes a human-approved spec, gathers deterministic evidence from the repository, asks an LLM judge only about what a rule cannot settle, and records every verdict in a hash-chained, signed ledger.

PASS SPEC-001 Criterion blocks are extracted from Markdown (1 check, 0.5s) PASS LED-004 Ledger writes are append-only (3 checks, judge 0.92) FAIL CHK-002 A failing grep produces FAIL (2 checks, 0.4s) 1 grep: 0 match(es) for "export function verifyChain" in src/**/*.ts 2 pass, 1 fail, 0 unverifiable, 0 skipped → exit 1 seq 175 prev 587f3e3c… hash 68d2bc82… sig ecdsa-p256-sha256

Command line

npm i -g @byspec-dev/cli then byspec init, byspec lint, byspec verify. Runs locally and in any CI.

GitHub App

Every pull request verified in an isolated sandbox, with per-criterion annotations and a downloadable evidence packet. Early access is opening soon.

Rules before models

A criterion with no checks is never a pass. The judge sees only the evidence a criterion declares, never the diff.