# Classification & Routing

Use this category for programs where Jev sorts incoming state into categories or picks the next destination — tickets, intents, alerts, documents, or traffic.

## Submission format

```md
- [Name](URL) - Industry: one-sentence description of the Jev use case.
```

## Entries

- [Diffusion Jev](https://github.com/Hangzhi/diffusion-jev-sglang) - Visual classification: independent Jev-style DiffusionGemma/SGLang server that selects doodle and flower labels from image pixels with typed Choice questions and displays candidate scores in a drawing playground, with public evaluation artifacts and uncalibrated probabilities.
- [Notra](https://github.com/usenotra/notra) - Marketing analytics: production GEO platform whose `NOTRA_JEV_CLASSIFIERS` flag routes brand-visibility classifiers off an LLM and onto Jev `Boolean` decisions at a 0.5 threshold, targeting 300 ms p50.
- [jev-router](https://github.com/gargpratyush/jev-router) `{agent: multi}` - Developer tooling: routes Claude Code tasks to the cheapest capable model by asking Jev to choose among candidates.
- [jev-router (prismhq)](https://github.com/prismhq/jev-router) - LLM infrastructure: open-source LiteLLM-based router where a Jev decision picks which model serves each request.
- [pi-jev-router](https://github.com/mejiasd3v/pi-jev-router) `{agent: pi}` - Coding agents: adds automatic per-request model routing to the Pi coding agent through Jev decisions on Vercel AI Gateway.
- [jcm-router](https://github.com/adarshmishra07/jcm-router) - Coding agents: local proxy that picks the Claude model and reasoning effort per message with a Jev decision while leaving the cached main chat untouched.
- [Codex Jev Router](https://github.com/suenot/codex-jev-router) `{agent: codex}` - Coding agents: asks Jev Choice and Noul questions about a short task summary to select a Codex subagent model and reasoning effort, with confidence thresholds and a Sol fallback.
- [Jev Auto Router](https://github.com/miniLV/Jev-Auto-Router) `{agent: codex, type: proxy}` - Coding agents: per-call Codex GPT routing where Jev makes one typed Choice over host-available (model, effort) pairs; a local Responses proxy keeps the tool loop continuous, then independent verification and Router Compass record whether the task still passed (prototype).
- [jev-agent-skill-router](https://github.com/GodsBoy/jev-agent-skill-router) - Agent infrastructure: routes agent skill selection through typed, confidence-aware Jev decisions so weak matches are declined instead of guessed.
- [typesafe-jev CV screener](https://github.com/gtaras7/typesafe-jev) - Recruiting: screens a folder of CVs with Jev typed judgments against an editable policy, re-scoring candidates for free when the policy changes.
- [Jev email intent workflow](https://github.com/GiesN/typesafe-jev-workflow) - Back-office automation: async LangGraph workflow gets a typed Jev `Choice` (`invoice` or `general`) and routes each inbound email to the matching handler.
- [DiffJury](https://github.com/raihankhan-rk/diffjury) - Code review: routes each pull request by risk with Jev before a human reviewer is assigned, doubling as a review coach.
- [HA-Jev](https://github.com/AboveColin/HA-Jev) - Smart home: Home Assistant integration that answers questions about the house as a probability, a choice, or a score.
- [secondlayer](https://github.com/ryanwaits/secondlayer) - Fault triage: self-hosted Stacks data service whose Slack gate and fault-triage paths both run on Jev decisions.
- [jev-logtriage](https://github.com/jyatesdotdev/jev-logtriage) - On-call operations: batches collapsed Loki logs into one Jev call of Noul, Score, and Choice questions, then maps answers in code to suppress, watch, review, notify, or page, with low confidence going to review and nothing executed.
- [new-api-typesafe-plugin](https://github.com/FFatTiger/new-api-plugin-typesafe) - LLM gateway: adds a native `/v1/systemone` endpoint to new-api so typed decisions sit behind the same gateway as chat models.
- [duet-agent](https://github.com/dzhng/duet-agent) - Agent harness: keeps a Jev-backed routing table for deciding which model should serve a request.
- [omo-jevlike-router](https://github.com/islee23520/omo-jevlike-router) - Skill routing: shrinks the skill catalog in a system prompt with one forward pass over a frozen Qwen, routing each request Jev-style.
- [jev-cookbook](https://github.com/nexibeo/jev-cookbook) - Developer education: 15 runnable Node recipes that route support tickets, file documents, categorize bank transactions and label Gmail with Jev `Choice` and `Noul` questions, sending low-confidence answers to human review.
- [flue-jev-demo](https://github.com/matthewp/flue-jev-demo) - Agent routing: routes a Flue agent's work with Jev through Cloudflare AI Gateway.
- [DocJev](https://github.com/jerryjliu/docjev) - Document pipelines: LlamaIndex's open-source library that classifies a document against natural-language category rules or finds the boundaries between sub-documents, with swappable OCR backends (liteparse or LlamaParse) and a benchmark harness whose 40-document pilot classified 40/40 originals correctly at about 182 ms Jev decision p50.
- [jev-fit](https://jev-fit.com) - Developer tooling: hosted fit checker that sends a pasted software idea and a fixed typed rubric to Jev in one call, where a `Choice` picks plain code, Jev or a reasoning LLM behind a `Noul` gate for non-tasks, code vetoes Jev when the idea needs images, and low confidence returns "not sure"; closed source, free page and API.
- [jev-skill-router](https://github.com/shimo4228/jev-skill-router) `{agent: claude-code, type: plugin}` - Coding agents: Claude Code plugin whose UserPromptSubmit hook asks Jev one `Choice` over the installed skill roster plus `Boolean`-style gates on whether any skill is needed, suggests a skill only when the gate and the per-candidate fit both clear 0.30, and defaults to a shadow mode that logs the decision without injecting it.
- [Jev Wrapped](https://github.com/gaborishka/jev-wrapped) - Media analysis: reads up to 1,500 posts from the last year of a public Telegram channel and asks Jev a `Choice` over ten kinds of post plus three `Noul` questions (paid ad, clickbait, emotional pressure) about each, counting an ad from 0.7, or from 0.4 when the kind is also ad, and clickbait and pressure from 0.5, then draws the monthly mix on a shareable card that links the highest-scoring posts for a manual check.
- [Jev-Mail](https://github.com/vynnlee/jev-mail) - Email productivity: runs a 24/7 Gmail classifier on user-owned Google Apps Script where Jev scores urgency, importance, and category, routing uncertain or suspicious mail to Review without a local daemon.
- [AI-decision-maker](https://github.com/zlZayn/AI-decision-maker) - Data cleaning: asks Jev `Choice` questions to classify CSV columns into a 13-code type vocabulary and each dataset into one of six scenes, then executes every write locally; measured Jev at 6.6–12.7× an LLM's token cost on this task because the output is already one character while per-question criteria repeat.
- [hearth-jev-rental-search](https://github.com/Nancy-Chauhan/hearth-jev-rental-search) - Housing search: autonomous multi-source rental search where Jev decides which listings match the criteria.
- [pi-jev-skill-picker](https://github.com/safzanpirani/pi-jev-skill-picker) `{agent: pi}` - Coding agents: ranks the Pi agent's installed skills against the current task with Jev before any of them run.
- [Jevonian](https://github.com/xinyao27/jevonian) - Coding agents: local OpenAI/Anthropic-compatible proxy where one Jev call picks both the model route and the thinking level for `jevonian/auto` from session state, quota health, candidate capabilities, and cache-switch penalties, after deterministic code has filtered candidates and while pinned models, explicit `jevonian/<route>` requests, and `routing.mode: "off"` skip Jev entirely; `minConfidence` marks a low-confidence route in the ledger rather than accepting it, and the ledger records the serving model and why.
- [Switchboard](https://github.com/ruban-24/switchboard) `{agent: multi, type: proxy}` - Coding agents: open-source System One-powered router that automatically matches each Claude Code or Codex task to an appropriate model and reasoning effort, then keeps that choice stable for the conversation to preserve prompt-cache continuity; powered by Jev today, with Laya, Kev, and Cua-S1 coming soon.
- [Tab Sorter](https://github.com/AstonyCat/jev-tab-grouper) - Browser tooling: Chrome MV3 extension that groups every tab in the window into named, colored Chrome tab groups from one parallel Jev call — one `Choice` question per tab against user-editable group criteria — with unclassified tabs falling to a fixed fallback bucket, manual groups untouched, and the pre-grouping tab order restored on ungroup; an optional LLM engine with self-invented group names is included for comparison runs.
- [Feed Lens](https://github.com/SkywalkerDarren/feed-lens) `{type: extension}` - Social media: uses Jev `Noul` judgments against per-platform, user-defined topic and expression labels to annotate Weibo, Threads and X posts directly in a Chrome extension.
- [jev-table-import-mapper](https://github.com/DuvInc/jev-table-import-mapper) - Data import: maps an uploaded CSV's columns onto a destination table with a strict deterministic name-equality pass, then one Jev `Noul` per remaining (source, destination) pair plus a guard `Noul` per incoming column, mapping 10 of 10 columns of a 23-column export at 253 questions in one call, 915 ms, $0.0012, unmapped fields left visible above a 0.75 threshold rather than guessed.
- [jev-oncall](https://github.com/mingleiw/jev-oncall) - On-call operations: asks Jev one call of four typed questions per alert (`Noul` actionable, `Score` severity, `Choice` owning team, `Choice` duplicate-of), pages on P(SEV1)+P(SEV2) ≥ 0.80 and drops only below 0.20 when actionability agrees, sends the band between to a human who has 15 minutes to ack before it pages anyway, links duplicates into a cycle-broken incident graph so two alerts can never silence each other, and falls back to configured severity on any error or timeout; a published 300-alert run measured p50 418 ms, p95 1477 ms and $0.04 per 1,000 alerts, with the slowest call landing 151 ms short of the 2 s timeout.
- [Jevidence](https://github.com/peakevergreen/jevidence) - Developer education: Python sandbox asks Jev `Choice` and `Noul` questions about issue category and reproduction steps in opt-in live mode, then applies confidence and reproduction gates to propose a queue or review fallback without assigning the issue, with synthetic offline fixtures and policy tests.
- [JevBystander](https://github.com/Nisaka520/JevBystander) - Messaging: Android accessibility app that reads the visible WeChat chat window and answers one batched request of typed `Choice`, `Score` and `Boolean` questions to sort the peer's message into intent (10 options), an emotion distribution (9 options), urgency (0-3 `Score`) and a suggested reply posture (11 options), then shows exactly three toasts and takes no other action - no generated reply, no input injection, no screenshot or OCR, with a local alias-to-relation table passed as state so the same sentence is judged differently for a partner than for a colleague.
- [langchain-skill-router](https://github.com/deyna256/langchain-skill-router) - Agent infrastructure: per-turn skill routing for LangChain deepagents, where Jev ranks the SKILL.md catalog against the request and the recent conversation and verifies the top candidates, so only the picked skill's instructions reach the prompt; the judge is a protocol that a self-hosted model or static rules can implement instead.
- [jev-rental](https://github.com/klauswg/jev-suite/tree/master/jev-rental) - Consumer rental: sorts every claim in a rental listing into verify-on-site / demand-evidence / high-risk-pitch buckets to build a pre-viewing checklist with code-templated questions; 50-sample calibration reports 0.910 gated accuracy and 0/10 injection flips.
- [jev-resume-disqualifier](https://github.com/AiPersonacademy/jev-resume-disqualifier) - Recruiting: knocks a resume out of a pipeline in under 25 ms by asking Jev the disqualifying question first, so only survivors reach a full evaluation.
- [Jev-IOT](https://github.com/pjmenon45/Jev-IOT) - Smart Utilities & Telecommunications: Ultra-low-cost, non-autoregressive AI telemetry classifier enabling sub-150ms anomaly triage and autonomic remediation across 10M+ smart meters for under $35/month.
- [AgentScope](https://github.com/agentscope-ai/agentscope) - Multi-agent platforms: multi-agent platform by Alibaba implementing native TypeSafe Jev classification models for binary, choice, and score routing across agent pipelines.