User repository on GitHub
Sub-second code diff, commit, and doc quality gate powered by TypeSafe AI Jev SystemOne
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Tools & CLIs
JevCI
CLI quality gate that asks four typed questions about each change - three Score lenses for commit quality, doc alignment and breaking-API risk, plus a Noul secret audit - and fails a diff, commit message or doc set below the resulting 0-100 score. Runs from a terminal, a git pre-commit hook or a GitHub Action.
- Stars
- 0
- Language
- JavaScript
- Published by
- Community
- Last verified
- Oct 2026
About this project
JevCI brings zero-latency quality enforcement to your terminal, git pre-commit hooks, CI/CD pipelines, and GitHub Actions. Instead of waiting 30–60 seconds for slow autoregressive LLMs, JevCI leverages Jev's fast System 1 primitives (score and noul) to evaluate pull requests and code changes with sub-second end-to-end latency (100–250ms model inference). ⚡ Sub-Second Total Latency: Runs 4 parallel quality rubrics end-to-end in <1s (20x faster than traditional 20–45s LLM evals).
Quoted from the project's README. Read the full README.
- Languages
- JavaScript
- Platforms
- CLI
- Capabilities
- Open sourceRequires API keyRuns locally
Highlights
- Four parallel rubrics with configurable weights and a default pass threshold of 70/100.
- Runs in a local simulation mode without TYPESAFE_API_KEY for offline testing.
- Outputs a terminal dashboard, GitHub PR comment Markdown or JSON reports.
- README includes Husky and GitHub Action integrations ready to copy.
Watch out
The README shows an MIT badge but GitHub reports the license as NOASSERTION, so no SPDX id could be verified. Its sub-second latency and cost claims depend on the hosted Jev service, and without an API key the gate runs in simulation mode only.
Questions about this entry
Short answers drawn from the linked project or page.
Four lenses: commit message quality, README and public API doc alignment with code changes, breaking API risk from changed signatures or removed exports, and a yes/no secret and security audit. The weighted scores combine into a 0-100 gate with a Jev rating confidence percentage.
Yes. Without TYPESAFE_API_KEY it runs in local simulation mode for instant offline testing; the live model needs a key. The same CLI works from the terminal, a git pre-commit hook or the included GitHub Action workflow.
The four parallel rubrics have configurable weights in jevci.config.json, which the README shows defaulting to 0.25 each for commit_quality, doc_alignment, breaking_risk and security_audit, with a pass threshold of 70 out of 100 and a diffTarget of HEAD~1. The target is overridable per run with --target, for example --target main...HEAD --threshold 80.
The README claims sub-second end to end with roughly 100 to 250 ms model inference, sold as about 20 times faster than a traditional 20 to 45 second LLM eval. That depends on the hosted Jev service, and without a key the gate runs in simulation mode only. The README shows an MIT badge but GitHub reports the license as NOASSERTION, so no SPDX id could be verified.
An ANSI terminal dashboard with a status table and score bars, GitHub PR comment Markdown, or JSON reports for custom CI integrations, selected with --format cli, markdown or json and optionally written with --out. The bundled Action checks out with fetch-depth 2, runs npx jevci on Node 20, and posts the Markdown report as a PR comment.
Two ways are documented. Write a .git/hooks/pre-commit shell script that echoes a banner and runs npx jevci --target staged --threshold 70, then chmod +x it, or install Husky, run npx husky init, and put the same command in .husky/pre-commit. Node.js 20 or newer is the stated requirement.
Clone the repo, npm install, then run npx jevci against the working repo, which defaults to the HEAD~1 diff target. Point it elsewhere with --target staged, a range like main...HEAD, or a literal commit, and override the message it grades with --commit. Node.js 20 or newer is the stated requirement, and TYPESAFE_API_KEY in the environment switches it from simulation mode to the live model.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Thread on Selmar's Jev code-review calibration notes and ordering.py comparisons.
Lectem2 pointsCalibrating Jev as a Code ReviewerRead the thread on Hacker NewsHacker News: Jev classifies agent PR hunks as P0, P1, or P2 so reviewers see P0 first.
namanbhulawat47 pointsJev Based Code ReviewRead the thread on Hacker NewsX: Magic Jev Ball for code review
X: jev-review: a local-first score loop for coding agents
More Jev resources like this
11GitHub stars
Open-source, pre-alpha CLI that runs plain-English browser tests on Playwright, using Jev for bounded decisions: resolving each step, picking elements among offered candidates and judging verify claims with probabilities. Bring your own TypeSafe key; MIT licensed.
Jev Tools & CLIs#community#e2e-testing#playwright
Community
sedum-dev/sedumTypeScript
sedum-dev/sedumTypeScript11GitHub stars
Fuzzy linter hook for Claude Code and Codex: after the agent edits a file, it sends the added code to Jev, which answers Noul checks against team rule packs in about 0.3 seconds, letting the agent fix violations before code review.
Jev Tools & CLIs#community#linter#claude-code
Community
ckorhonen/jev-lintHTML
ckorhonen/jev-lintHTML1GitHub stars
Go linter whose rules are plain-English questions: AST matchers select nodes and Jev answers one Noul per fragment above the rule's threshold. It runs standalone, under go vet, and as a golangci-lint plugin, with cached answers so runs only ask about changed code.
Jev Tools & CLIs#community#linter#go
Community
arturobermejo/semcheckGo
arturobermejo/semcheckGo140GitHub stars
A local Chrome extension plus CLI that classifies each agent PR hunk as P0, P1, or P2 with Jev, showing P0 by default and human-readable diff summaries.
Jev Tools & CLIs#community#code-review#typescript
Community
egma-ai/jev-code-reviewerJavaScript
egma-ai/jev-code-reviewerJavaScript8GitHub stars
Supervisor for unattended coding agents: it tracks cross-turn state and asks one batched Jev Choice whether a trajectory should continue, pause or escalate, while deterministic code owns dangerous-command blocking, budget caps and Ed25519-signed receipts.
Jev Tools & CLIs#community#guardrails#safety
Community
VeridicalTech/EdwardPython
VeridicalTech/EdwardPython4GitHub stars
CLI and Python library that runs declarative YAML judgment tasks - classify, route, score, verify - natively on Jev Choice/Score/Noul, on any OpenAI-compatible backend, or on local keyword rules, with confidence gates, fallbacks and per-decision cost records.
Jev Tools & CLIs#community#yaml#classification
Community
lexingtonhibiki/judgekitPython
lexingtonhibiki/judgekitPythonFrom the Jev guides
Original write-ups on what this entry is for.
The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.
Jev Tools & CLIs#gateway#vercel#cloudflare
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.
Jev Tools & CLIs#classification#email#security
Read article
From the Jev community
Posts from builders shipping with Jev right now.