AI Rank
中文
← Open Source
devagrawal09

jev-review

A staged code-review workflow and local dashboard built with TypeSafe Jev.

AI EngineeringBuild agent UIBuild agent workflow (SDK)TypeScript
Open on GitHub
Momentum
+2stars in 24 hours+0.3%
688
Stars
45
Forks
+11
This week
1
Contributors
Created 2026-09-16 · Updated 2026-10-16 · #4176 today
Top developers
devagrawal09

devagrawal09/jev-review is ranked 4,176 with 688 stars.

Same-category comparison

devagrawal09/jev-review is ranked 4,176 among these 8 peers; buzzer-re/Rikugan is ranked 4,175.

Same-category comparison
NameRankMetrics
jaredrhod/ai-memory-vault4,167
Stars:
702
Forks:
187
Description:
Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No vector database, just markdown.
GPT-AGI/Clawd-Code4,168
Language:
Python
Stars:
701
Forks:
345
Description:
Claude-Code-Python: Reconstructing Claude Code in Python.
samuelfaj/distill4,170
Language:
Rust
Stars:
698
Forks:
43
Description:
Get FAR MORE done with FAR FEWER tokens 🔥.
buzzer-re/Rikugan4,175
Language:
Python
Stars:
689
Forks:
77
Description:
A reverse-engineering agent for IDA Pro and Binary Ninja.
Pluviobyte/video-production-skills4,178
Language:
Python
Stars:
676
Forks:
83
Description:
Reusable AI video production skills library for creation, recreation, motion design, openers, and QA.
ThibautBaissac/rails_ai_agents4,182
Language:
Shell
Stars:
668
Forks:
83
Description:
Specialized AI skills, agents, rules and hooks for modern Rails AI driven-development + Spec-Driven-Development kit + MCP.
plannotator/herdr-annotate4,183
Language:
Rust
Stars:
668
Forks:
22
Description:
Annotate terminal text, review documents and agent replies in Herdr, and send the feedback straight back to the agent.
java-up-up/nexus-agent4,185
Language:
Java
Stars:
663
Forks:
102
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguageTypeScript
CategoryAI Engineering
SubcategoryBuild agent UI, Build agent workflow (SDK)
KeywordsAutomation, Coding, Guardrails, Structured outputs
Stars688
Forks45
Contributors1
Created date2026-09-16
Updated date2026-10-16
Stars in 1 day2
Stars in 7 days11
Rank4,176
Previous rank6,621
Rank change2,445
7-day stars rank3,871
Previous 7-day stars rank4,287
7-day stars rank change416
Total stars rank15,076
Previous total stars rank15,082
Total stars rank change6
README summary

Jev Review 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. How It Works 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. Selects concrete diff hunks or source regions before scoring impact. Uses structured hints, counterexamples, and explicit decision boundaries. Applies thresholds and workflow policy in code. Shows large reports in collapsible dashboard sections. Binds the dashboard to and never serves environment files. Current Scope This is an experiment in composing fast typed judgments into a review workflow. It does not yet integrate compiler diagnostics, static analyzers, repository indexing, or generated explanations. Findings are review prompts, not proof of

a defect.

Frequently asked questions

How many stars and forks are recorded?

devagrawal09/jev-review has 688 stars and 45 forks.

What is the repository rank?

devagrawal09/jev-review is ranked 4,176.

What language and category are recorded?

devagrawal09/jev-review has 688 stars, uses TypeScript and belongs to AI Engineering.

Which repository is closest in rank?

devagrawal09/jev-review is compared with buzzer-re/Rikugan, ranked 4,175 with 689 stars.

README

Jev Review

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.

How It Works

The reviewer keeps orchestration in code and uses Jev for bounded judgments:

Noul risk matrix
  -> Choice + Score file profiles
  -> Choice evidence selection
  -> Choice mechanism classification
  -> Score severity
  -> conditional Choice reviewer routing
  • 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.
  • Selects concrete diff hunks or source regions before scoring impact.
  • Uses structured hints, counterexamples, and explicit decision boundaries.
  • Applies thresholds and workflow policy in code.
  • Shows large reports in collapsible dashboard sections.
  • Binds the dashboard to 127.0.0.1 and never serves environment files.

Quick Start

Requires Node.js 24+, Git, and a TypeSafe API key.

npm install
cp .env.example .env
# Add TYPESAFE_API_KEY to .env

# Review the current Git diff
npm run review:changes:save -- /path/to/git/repository

# Or scan every non-ignored source file under a scope
npm run review:codebase:save -- /path/to/git/repository-or-package
npm run dashboard

Open http://127.0.0.1:4317.

Commands

Command Purpose
npm run review:changes -- Print a current-diff review as JSON
npm run review:changes:save -- Save a current-diff review for the dashboard
npm run review:codebase -- Print a complete codebase scan as JSON
npm run review:codebase:save -- Save a complete codebase scan for the dashboard
npm run dashboard Start the local dashboard
npm run check Typecheck, verify dependency flow, and syntax-check the dashboard client

Architecture

Everything lives under src/, arranged in layers that only depend downward:

src/
  domain/      config.ts, types.ts, patch.ts   shared policy, report shapes, diff parsing
  adapters/    git.ts, repository-files.ts     change and complete-source discovery
               report-store.ts                 atomic report save/load
  review/      changes.ts, codebase.ts          mode-specific workflows
               *-judgments.ts, workflow.ts     Jev calls and shared staged orchestration
  cli/         review-*.ts, save-*.ts           explicit mode entry points
  dashboard/   server.ts, public/              local-only HTTP server and the plain client

Imports point toward lower layers only:

{ cli, dashboard } -> review -> adapters -> domain

scripts/check-dependencies.ts fails npm run check on any upward import, any import between cli and dashboard, or any cycle.

Current Scope

This is an experiment in composing fast typed judgments into a review workflow. It does not yet integrate compiler diagnostics, static analyzers, repository indexing, or generated explanations. Findings are review prompts, not proof of a defect.

License

MIT

Nearby in the ranking
Similar items