Code review, PR labelling, linting, test selection and semantic code search on Jev. Every entry links to its source and shows the figures its author published.
50 builds · page 1 of 2
Niaz Morshed
@niazmorshed_
built `jev-review` @typesafeai it's an experimental, local-first MCP plugin that gives coding agents a score quality feedback loop across different metrics. agents call jev while they work, get scored, make improvements, and repeat the loop try below 👇
XCoding and code review
Raihan Khan
@raihankhan_rk
I got access to Jev by @typesafeai today morning and I built a cool use case for it Introducing DiffJury - simply paste any public PR link and Jev tells you immediately if it's safe to merge or does it require review ✅ 🔗 Feel free to try it out here - http://diffjury.up.railway.app Imagine Jev being able to tell you if you should merge a PR with grounded context of your codebase. that's what we're building at @graphify 👀 It's fascinating how insanely fast Jev is... the model architecture in itself is quite interesting and this has opened up a plethora of new use cases and I'm sure the internet will pick up on it sooner than anyone'd expect
Live siteCoding and code review
Oskar
@o_kwasniewski
e2e + jev from @typesafeai ⚡ I'm building an open-source framework for running e2e tests with agents. supports web, mobile (and more!) available soon: tester.army/e2e
XCoding and code review
Sponsored
One card in the feed, every twelve, on every page of it. $100 a week, cancel any week.
GitHubCoding and code review
A GitHub Action that reviews and classifies PRs with Jev alone.
wang2
3
GitHubCoding and code review
A fuzzy linter: Jev gives your code an ocular patdown.
Tyler Nieman
15
SkillCoding and code review
An agent skill that sends a coding agent’s closed judgments to Jev.
HyunjunJeon
6
GitHubCoding and code review
A staged code-review workflow with a local dashboard.
Dev Agrawal
686
GitHubCoding and code review
GitHub PR labels chosen by Jev, with size measured as scope, not lines.
Jeremy Huang
4
GitHubCoding and code review
Turn an agent skill into an Oxlint plugin that asks Jev.
Tony Powell
1
Oursshippile.com
GitHubCoding and code review
Cucumber tests from the .feature file alone. No step definitions.
Michael Poage
3
GitHubCoding and code review
Semantic code search for coding agents, benchmarked on SWE-bench Lite.
Bently
82%
GitHubSDKs and integrations
A Rust CLI for Jev, with a linter that checks questions before you pay.
Ariel Frischer
4
GitHubSocial feeds
A prose linter for AI writing tells: regex rules plus Jev for judgment.
Daniel Willoughby
35
Saeed
@stringsaeed
built a highlighter on jev paste any language → my code tokenizes → jev names the lang, colours every word, then says which of 9 lint rules fire and where nine rules in code. jev just answers. near instant lab.saeed.sh/highlight
Jason Lu
@jasonlu_ai
JEV is changes the world of E2E testing! Same eBay test flow, completed-run medians: Jev: 47s / $0.0067 GPT-5.6 Luna: 62s / $0.0277 Claude Sonnet 5: 79s / $0.4062 Try jev-e2e. github.com/perixtar/jev-e…
GitHubSecurity and abuse
Bug-hunting crawlers built from five Unix-style primitives.
russfranky
GitHubCoding and code review
OpenAPI compatibility checks, structural and semantic.
Shuhan Sun
5
GitHubCoding and code review
Semantic code search for agents: find behaviour, not strings.
Nassim Arifette
104
GitHubCoding and code review
A pull request approver that asks Jev before it approves.
MetalBear
9
GitHubContext and memory
Every tool result is filtered by Jev before the model reads it.
AstroHan
6
GitHubCoding and code review
Checks generated code against the specification that asked for it.
Nozomi Koborinai
11
GitHubCoding and code review
Three Claude Code hooks that each ask Jev a question.
Jake Reardon
0
GitHubCoding and code review
Reads a finished coding session and judges each turn.
Zach Hobbs
0
Wayne Nilsen
@waynenilsen
Jev to unslop Jev as slop linter
XSocial feeds
檀奕
@yunxi0623
分享个很火的 skill： typesafe-ai Skill 👇 安装命令：npx skills add typesafe-ai/skills --skill typesafe-ai 可以直接 让 Codex 理解 TypeSafe / Jev 的调用方式 它最有意思的地方，不是让 Jev 替 Codex 写代码，而是把代码里的“判断题”交给 Jev 不过注意它不是装完就会自动接管 Codex 的所有决策，你需要在 Prompt 或代码里明确哪些判断交给 TypeSafe
XCoding and code review
GitHubCoding and code review
Score every test against a git diff, then emit the runner arguments.
mizchi
36
GitHubCoding and code review
Codebase search by sending a hundred walkers through the file tree.
Ellipsis
99Stars as GitHub showed them on Oct 15, 2026.
| Build | By | Reported |
|---|---|---|
| siftr | Bently | Right file in top 5: 82% · Search time: ~2 s |
| A syntax highlighter on Jev | Saeed | Lint rules: 9 |
| jev-e2e | Jason Lu | Jev: 47 s / $0.0067 · Sonnet 5: 79 s / $0.4062 |
| Canny | Qkal | Judgment: ~0.25 s |
| AgentJev-0.6B | malevrigns | Coding accuracy: 57.8% (606/1048) · Correct patch ranked first: 348 / 524 |
| jev-permission-gate | Madison Rickert | Permission checks: 2x faster |
| mu | qybaihe | Decision points per turn: 38 |
Each figure is the author’s own, not measured by this site.