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
Knowledge Signal
A Show HN prototype that turns study notes into a confidence-aware knowledge profile by scoring them with Jev.
- Stars
- 0
- Language
- JavaScript
- Published by
- Community
- Author
- sumant1122
- 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.
Used inJev for Education
Highlights
- Posted on Hacker News on 25 September 2026, 3 points and no comments.
- The author calls it an open-source prototype for rubric assessment of study notes.
- Profiles are confidence-aware because the scores come from Jev.
Watch out
A prototype with a quiet thread. No published accuracy on labelled notes.
Questions about this entry
Short answers drawn from the linked project or page.
The captured README documents JevCI, a diff and commit-message quality gate that scores pull requests. The entry copy describes a study-note rubric prototype instead. The source does not document the study-notes workflow, so the two descriptions are unreconciled.
Per the README, four lenses run in parallel: commit message quality, README and public API doc alignment, breaking API or removed-export risk, and a secret and security audit using the yes/no primitive. Each returns a 0 to 100 score plus a confidence, weighted by config.
No, and that is the catch. The README says that when TYPESAFE_API_KEY is unset the tool runs in local simulation mode for offline testing, so scores from a keyless run are not model output and should never gate a merge.
No. The README quotes roughly 100 to 300 milliseconds and about $0.042 per million tokens as TypeSafe's own numbers, and compares itself to 20 to 45 second LLM evaluations. It publishes no accuracy on labelled diffs of its own.
Git clone the repository, run npm install, then npx jevci on the current changes. Set TYPESAFE_API_KEY for the live model, otherwise it runs in local simulation mode for offline testing.
Commit message quality, doc and code alignment, API contract and breaking risk, and secret and security audit, each returning numerical scores and calibrated probability match confidence.
Add a .github/workflows/jevci.yml job that runs npx jevci --threshold 70 --format markdown with TYPESAFE_API_KEY as a secret, or wire the same command into a git pre-commit hook or Husky.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Knowledge Signal scores study notes with Jev into a confidence-aware profile.
paperplaneflyr3 pointsShow HN: Knowledge Signal – A JEV-powered rubric assessment tool for study notesRead the thread on Hacker NewsMore Jev resources like this
536GitHub stars
A Python framework where an authoring LLM writes a task-specific Jev harness, then optionally evolves it using reward reflection and GEPA over full trajectories.
Jev Tools & CLIs#community#python#agents
Community
TianyuCodings/JevHarnessPython
TianyuCodings/JevHarnessPythonUse Jev as a Braintrust judge scorer, then inspect selected answers, confidence, and probabilities alongside the scorer answer. Includes tracing for your own calls.
Jev Tools & CLIsArticle#community#evaluation#observability
Community
824GitHub stars
Vercel Labs' terminal CLI for the AI SDK: its `ai evaluate` command answers named Boolean, Choice, and Score questions, with Jev as the default evaluation model and one unchanged input shared across all questions.
Jev Tools & CLIs#community#typescript#cli
Community
vercel-labs/ai-cliTypeScript
vercel-labs/ai-cliTypeScript307GitHub stars
An experimental Sutro CLI that evaluates CSV, Parquet, and JSONL data with Jev, asks you to label ambiguous and random audit rows, and uses GEPA to propose improved function definitions.
Jev Tools & CLIs#community#python#cli
Community
sutro-sh/jev-alignPython
sutro-sh/jev-alignPython152GitHub stars
A CLI that scores code quality by asking Jev yes/no questions about each file, runs your existing test command, and turns uncovered paths into small actionable queries for agents.
Jev Tools & CLIs#community#rust#cli
Community
supercorp-ai/supercovRust
supercorp-ai/supercovRust106GitHub stars
A collection of 26 production-ready agent skills for Claude Code, Cursor, Kiro, Windsurf, and OpenCode; four skills call TypeSafe Jev for calibrated Score and Noul judgments and fall back to heuristics when it is unavailable.
Jev Tools & CLIs#community#python#skills
Community
fabricioctelles/skillsPython
fabricioctelles/skillsPythonFrom 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.