EVERY ENTRY HAS RECEIPTS

AWESOME
JEV

Open-source directory

Every project here really calls Jev in its source · refreshed daily

788projects
182runnable here
765code receipts

ALL 788 PROJECTSEvery project

src/review/codebase-judgments.ts
questions: {
  correctness: boolean,
  security: boolean,
  reliability: boolean,
  // +2
}
runnable
@devagrawal09367

jev-review

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

Guardrails & reviewTypeScript
tests/jev.test.ts
questions: {
  s0: boolean,
  s1: boolean,
}
runnable
@wobsoriano14

oxlint-plugin-jev

Lint rules written in plain English. Oxlint finds the code, TypeSafe Jev answers the question.

Guardrails & reviewTypeScript
scripts/probe-jev-input-size.mjs
questions: {
  noul: boolean,
}
runnable
@tyler-dot-earth10

patdown

typesafe's jev as a "fuzzy linter". give your code an ocular patdown.

Guardrails & reviewTypeScript
src/spam.ts
questions: {
  unsolicited_promotion: boolean,
  profile_bait: boolean,
  scam_or_phishing: boolean,
  // +5
}
runnable
@backmeupplz4

jev_antispam_bot

Minimal grammY Telegram anti-spam bot powered by TypeSafe Jev

Guardrails & reviewTypeScript
src/tools.ts
questions: {
  instructions: boolean,
}
runnable
@Nyarlathoteppppp3

pi-heed

Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.

Guardrails & reviewTypeScript
jev-moderation.ts
questions: {
  blocking: boolean,
}
runnable
@CodeAlive-AI2

mastra-jev-moderation

Input moderation for Mastra agents on TypeSafe Jev — one file

Guardrails & reviewTypeScript
demo/js/client-screener.js
questions: {
  is_toxic: boolean,
  is_profane: boolean,
  severity: score,
  // +2
}
runnable
@ItisShikhar2

gg-friggin-ez

Fast, drop-in profanity and toxicity screener for Node.js, powered by TypeSafe AI Jev. Catches leetspeak, character spacing, and romanized profanity across languages including Kannada, Telugu, Tamil, Hindi, and Bengali. ~50-500ms latency.

Guardrails & reviewTypeScript
packages/decision-provider/test/openrouter.live.test.ts
questions: {
  wants_refund: boolean,
  intent: choice,
}
runnable
@omkarghugarkar0072

actiongate-jev

Runtime authorization and guardrails for AI-agent tool calls with deterministic policy and TypeSafe Jev via OpenRouter.

Guardrails & reviewTypeScript
src/safe_sh/__init__.py
questions: {
  file_removal: score,
  credential_theft: score,
  data_exfiltration: score,
  // +5
}
runnable
@EpicEric1

safe-sh

Static shell script analysis with Jev.

Guardrails & reviewNix
test/jev.test.mjs
questions: {
  uses: boolean,
}
runnable
@fatwang21

jev-review-action

Configurable GitHub submission review and PR classification with TypeSafe Jev. No text-generation model.

Guardrails & reviewJavaScript
src/jev.ts
questions: {
  should_review: boolean,
  risk: choice,
  route: choice,
  // +1
}
runnable
@NemanjaManic1

ci-gatekeeper-bot-jev

GitHub Action that uses Jev (TypeSafe AI via Vercel AI Gateway) to cheaply triage pull requests before expensive LLM/human review

Guardrails & reviewShell
scripts/probe-limits.mjs
questions: {
  condition: choice,
}
runnable
@Victor-Casado1

if-ai

Plain-English pull request checks powered by Jev. One condition, a minimum confidence, one check.

Guardrails & reviewTypeScript
src/systemone.js
baseUrl = 'https://api.typesafe.ai/v1',
@lakeday-org161

perch

Semantic code linting with Jev

Guardrails & reviewJavaScript
src/backend.ts
typesafe: { host: "api.typesafe.ai" },
@DevMortimer96

pi-warden

Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop

Guardrails & reviewTypeScript
typesafe/__init__.py
base_url: str = "https://api.typesafe.ai",
@brainstormity36

Jev-Moderation-Bot

A Discord moderation bot built with Python and TypeSafe AI (Jev System One). It filters spam and scam links in real time, escalates offenses automatically, and lets moderators prof

Guardrails & reviewPython
src/jev.rs
const ENDPOINT: &str = "https://api.typesafe.ai/v1/systemone";
@Eriskii15

ErisLint

Rust linter powered by configurable Jev rules, with a VS Code extension.

Guardrails & reviewRust
src/jev-client.ts
const response = await fetch("https://api.typesafe.ai/v1/systemone", {
@huntedman10

JevLint

Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

Guardrails & reviewTypeScript
benchmarks/bench_framing_weakens.py
"https://api.typesafe.ai/v1/systemone", data=body,
@anpicasso8

hermes-jev-approvals

PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.

Guardrails & reviewPython
agent/lib/judging/judge.ts
import { experimental_evaluate as evaluate } from 'ai';
@frostney6

clean-code-review

Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.

Guardrails & reviewTypeScript
extensions/risk-rules.ts
typesafeBaseUrl: "https://api.typesafe.ai/v1",
@TannerMidd6

specpi-jev-guard

Checks risky shell and file commands before your agent runs them.

Guardrails & reviewJavaScript
src/jev.ts
response = await this.fetcher("https://api.typesafe.ai/v1/systemone", {
@Reindeer-AI5

pi-jev-guard

Check Pi code edits against repository Markdown rules with TypeSafe Jev

Guardrails & reviewTypeScript
src/riff/doctype.py
from typesafe_sdk import AsyncTypeSafeClient, Choice, RetryPolicy, TypeSafeError
@scale-venture-partners5

riff

A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model

Guardrails & reviewPython
jev_commit/jev.py
DEFAULT_BASE_URL = "https://api.typesafe.ai"
@valentynkit5

jev-commit

pre-commit hook: one Jev call judges whether your commit message matches the diff, plus debug leftovers, scope creep, and a secret belt

Guardrails & reviewPython
src/lib/review.ts
import { choice, noul, score, TypeSafeClient } from "@typesafe-ai/sdk";
@raihankhan-rk4

diffjury

DiffJury — TypeSafe Jev PR risk router + code review coach

Guardrails & reviewTypeScript
scripts/jev_client.py
ENDPOINT = "https://api.typesafe.ai/v1/systemone"
@win4r3

jev-security-scan

使用 TypeSafe Jev 审查 Skill 与 MCP 可疑行为 | Review Agent Skills and MCP code with Jev, static evidence, and explicit coverage gaps

Guardrails & reviewPython
src/semantic-lint/evaluator.ts
} from "@typesafe-ai/sdk";
@andrueandersoncs2

jev-semantic-linter

A CLI that checks natural-language engineering rules against the current Git

Guardrails & reviewTypeScript
src/verify.mjs
import { experimental_evaluate as evaluate } from 'ai';
@caiovicentino2

jev-shield

Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.

Guardrails & reviewJavaScript
pkg/evaluator/typesafe.go
DefaultBaseURL = "https://api.typesafe.ai/v1/systemone"
@ClemensSchartmueller2

jev-guard

High-speed, cross-agent safety gate plugin for Claude Code, Codex CLI, and Antigravity.

Guardrails & reviewGo
src/cli.ts
TYPESAFE_BASE_URL           Jev API root (default https://api.typesafe.ai)
@godspede2

construct-auto-classifier

Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.

Guardrails & reviewTypeScript
lib/typesafe.ts
import { choice, TypeSafeClient } from "@typesafeai/sdk";
@opaielsheikh2

typesafe-migration-guard

Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model)

Guardrails & reviewTypeScript
src/jev_oas_sentinel/jev.py
DEFAULT_ENDPOINT = "https://api.typesafe.ai/v1/systemone"
@ShuhanSun2

jev-oas-sentinel

Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.

Guardrails & reviewPython
wince/core/questions.py
from typesafe_sdk import Choice, Noul, RetryPolicy, Score, TypeSafeClient
@TinyFrontier2

wince

Routes human review attention: green/yellow/red for a diff and who should look. It doesn't review the code. Built on TypeSafe.

Guardrails & reviewPython
src/pricing.ts
.parse(models.data.find((item) => item.id === "typesafe-ai/jev"));
@zdenham2

jev-lint

Lint JavaScript and TypeScript against plain-English project conventions with Jev.

Guardrails & reviewTypeScript
src/main.rs
let resp = ureq::post("https://api.typesafe.ai/v1/systemone")
@AkashPriyadarshii1

jev-git

Sub-second Git pre-commit & pre-push semantic reflex gate powered by TypeSafe AI Jev

Guardrails & reviewRust
src/config.rs
#[arg(long, default_value = "https://api.typesafe.ai/v1/systemone")]
@AlexBabescu1

ActionJev

Structured code review for GitHub and Gitea Actions, powered by TypeSafe Jev and written in Rust.

Guardrails & reviewPython
src/slop_linter/cache.py
from typesafe_sdk import SystemOneResponse
@almcc1

slop-linter

Lints AI-generated code for slop using Jev, a System One model that makes fast structured decisions instead of generating text.

Guardrails & reviewPython
sentinel/jev.py
MODEL = "typesafe/jev-1.13"
@bojansandhaus1

jev-home-assistant-sentinel

A safety boundary for AI-assisted Home Assistant decisions, with explicit policy checks and deterministic state verification.

Guardrails & reviewPython
src/config.ts
jevModel: process.env.JEV_MODEL ?? "typesafe/jev-1.13",
@CeamKrier1

semantic-firewall

Semantic firewall for LLM agents: tool calls gated by TypeSafe Jev (System One decision model via OpenRouter) + deterministic policy. PoC with corpus, stability eval, baseline, results.

Guardrails & reviewTypeScript
packages/engine/src/rule.ts
url: `${process.env.OXLINT_JEV_BASE_URL ?? DEFAULT_BASE_URL}/v1/systemone`,
@cephalization1

jev-oxlint

Digest your skills into oxlint rules powered by jev

Guardrails & reviewTypeScript
src/add_action/tests.rs
assert!(headers.starts_with("post /v1/systemone "));
@Infrawrench1

Jeeves

Twitch/Discord moderation rules in plain English, powered by Jev and Gemini

Guardrails & reviewRust
app/api/moderate/route.ts
import { TypeSafeClient, noul, score } from "@typesafe-ai/sdk";
@NorbertBodziony1

guard-jev

Moderation Guard — TypeSafe Jev demo

Guardrails & reviewTypeScript
jev_pr_review.py
TYPESAFE_URL = "https://api.typesafe.ai/v1/systemone"
@ohernandezdev1

jev-pr-review

Score every file in a pull request with Jev (TypeSafe System One) and decide in code whether it can merge itself. Shadow mode: comments, never merges.

Guardrails & reviewPython
index.ts
import { noul, score, TypeSafeClient } from '@typesafe-ai/sdk';
@santos-sanz1

jev-audio-beeper

Low-latency audio censorship POC using Jev typed decisions and ffmpeg.

Guardrails & reviewTypeScript
packages/core/src/backends/jev.ts
this.baseUrl = opts.baseUrl ?? process.env.JEV_BASE_URL ?? "https://api.typesafe.ai/v1";
@shubhangi0131

prune-review

Cost-aware PR review using TypeSafe Jev decisions before a generative reviewer.

Guardrails & reviewTypeScript
jev-comment-triage.php
$columns['jev_triage'] = __( 'Jev', 'jev-comment-triage' );
@soderlind1

jev-comment-triage

Async Jev-powered WordPress comment triage: background spam, scam/phishing, and toxicity moderation that keeps comment submission fast.

Guardrails & reviewPHP
src/cli.ts
import { noul } from "@typesafe-ai/sdk";
@Thestral121

pr-sieve

Semantic PR gate: .jev.yml rules as TypeSafe Jev questions. Not a review bot.

Guardrails & reviewTypeScript
principles.py
The `jev` decorator discards confidence, so this calls Jev through `typesafe_sdk` directly.
@uberto1

jev-test

Review Kotlin files against From Objects to Functions principles using Jev

Guardrails & reviewPython