User repository on GitHub
A staged code-review workflow and local dashboard built with TypeSafe Jev.
- Forks
- 45
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Jev Review — devagrawal09
A staged code-review workflow that uses Jev for bounded judgments over Git diffs or whole codebases, with a local dashboard. Policy and thresholds stay in code while Jev screens five risk areas.
- Stars
- 687
- Language
- TypeScript
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- devagrawal09
- Last verified
- Sep 2026
About this project
A small code-review workflow built with TypeSafe Jev. It can review a Git diff or scan a complete codebase, follows the strongest structured signals through focused model calls, and presents the result in a quiet local dashboard. The reviewer keeps orchestration in code and uses Jev for bounded judgments: Exposes separate change-review and complete-codebase entry points. Uses changed or related tests as context when judging test gaps. Screens correctness, security, reliability, compatibility, and test coverage.
Quoted from the project's README. Read the full README.
Used inJev for Security & Privacy
Highlights
- Reviews a Git diff or scans a whole codebase, printing JSON or saving reports for the dashboard.
- Screens correctness, security, reliability, compatibility, and test coverage.
- The dashboard binds to 127.0.0.1 and never serves environment files.
- npm run check enforces layer dependency rules and rejects upward imports.
Watch out
Findings are review prompts rather than proof of a defect; needs Node 24 or newer, Git, and a TypeSafe API key.
Questions about this entry
Short answers drawn from the linked project or page.
Neither, and the README says so: it is an experiment in composing fast typed judgments, with no compiler diagnostics, static analyzers, repository indexing or generated explanations. Findings are review prompts, not proof of a defect, so treat the output as a place to start reading rather than a verdict.
Orchestration stays in code. It runs a staged sequence - a Noul risk matrix, then Choice and Score file profiles, Choice evidence selection, Choice mechanism classification, Score severity, and a conditional Choice routing step - and applies thresholds and workflow policy in code rather than asking the model whether to continue.
It has two entry points: the current git diff and a complete scan of every non-ignored source file under a scope, which can be a repository or a package. Output prints as JSON or saves for a local dashboard that binds to 127.0.0.1, shows large reports in collapsible sections, and never serves environment files.
The key goes in .env: copy .env.example, add TYPESAFE_API_KEY, alongside Node.js 24 or newer and Git as the other stated requirements. Call count is where the docs go quiet. Every staged judgment is a separate request against your account, a scan covers every non-ignored source file under the scope, and the README gives no number and no cost estimate.
It needs Node.js 24 or newer, Git and a TypeSafe API key. Run `npm install`, copy .env.example to .env and add TYPESAFE_API_KEY, then `npm run review:changes:save -- /path/to/repo` for a diff or `npm run review:codebase:save -- /path/to/scope` for a scan, and `npm run dashboard`.
Correctness, security, reliability, compatibility and test coverage. It also uses changed or related tests as context when judging test gaps, and selects concrete diff hunks or source regions before scoring impact.
Layers only depend downward (cli and dashboard to review to adapters to domain), and `npm run check` runs scripts/check-dependencies.ts, which fails on any upward import, any import between cli and dashboard, or any cycle.
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
Other listings of this project
Forks and copies of this project in the directory. This entry is the canonical one.
A local-first MCP server that gives Claude Code, Codex, Cursor, and OpenCode structured quality scores from Jev across correctness, complexity, tests, security, and other dimensions while the agent writes code.
Jev Tools & CLIs#community#typescript#mcp
Community
NiazMorshed2007/jev-reviewTypeScript
NiazMorshed2007/jev-reviewTypeScriptJev Review runs as a local MCP server that gives Claude Code, Codex, Cursor and OpenCode structured quality scores while they work. This modified fork of NiazMorshed2007/jev-review adds strict 451-fallback validation with contract tests and a noul invariant-adjudication workflow.
Jev Tools & CLIs#community#github#mcp
Community
sabrina-fan/jev-reviewTypeScript
sabrina-fan/jev-reviewTypeScriptAutonomous PR review bot that consumes PR metadata and patches, asks Jev a finite set of typed questions across correctness, security and verification perspectives, then applies deterministic gates in code. Suggestions are advisory; it never edits or merges.
Jev Agents & MCP#community#jevbest#catalog-import
Community
thiago-ss/jev-reviewPython
thiago-ss/jev-reviewPythonMore Jev resources like this
Pi extension that supervises a coding agent with Jev judgments: it holds risky tool calls, checks writes against project Markdown rules, and feeds most issues back to the agent as a steer instead of interrupting you. The conscience is beta and off by default.
Jev Tools & CLIs#community#typescript#guardrails
Community
DevMortimer/pi-wardenTypeScript
DevMortimer/pi-wardenTypeScriptA Jev-first command-line coding agent: natural-language requests are routed by Jev to one of ten bounded review and triage workflows, and unsupported requests fall back to the Pi coding agent or a workflow Stanley stages for promotion.
Jev Tools & CLIs#community#typescript#cli
Communitydevagrawal09/stanley-codeTypeScript
devagrawal09/stanley-codeTypeScriptA Node CLI that sends source, configuration, build, and CI files to Jev and reports suspicious files and lines with probabilities, as a second opinion before running unfamiliar code.
Jev Tools & CLIs#community#typescript#cli
Community
luantak/is-maliciousTypeScript
luantak/is-maliciousTypeScriptAgent-ergonomic CLI following the AXI conventions that gives coding agents Jev judgments for blocking risky tool calls, screening fetched content for prompt injection, triaging logs, flagging risky diffs, and ranking many items. Routine commands are decided locally at no cost.
Jev Tools & CLIs#community#typescript#cli
Community
shiftynick/jev-axiTypeScript
shiftynick/jev-axiTypeScriptA semantic grep CLI that chunks files or staged diffs into 5-60 line pieces, packs 16 chunks and 16 Jev Noul questions into one request, and prints file:line hits above a probability threshold with grep-style exit codes.
Jev Tools & CLIs#community#typescript#cli
Community
kyu1204/jgrepTypeScript
kyu1204/jgrepTypeScriptA pre-commit hook that answers five Jev questions about the commit message and staged diff together, warning on mismatches and blocking only on a credential-shaped line.
Jev Tools & CLIs#community#python#coding-agent
Community
valentynkit/jev-commitPython
valentynkit/jev-commitPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.