Classification & Routing

Deterministic evidence selector for noisy Codex investigations; its earlier Jev subagent router is kept for the record, not recommended.

Confidence-aware skill router that uses Jev to pick agent skills from large catalogues, declining or asking for review on weak matches.

Open lab on using Jev routing in front of Claude Code correctly: measured bugs and patch, hard fallback, completion gate.

Claude Code hook that asks Jev which skill fits each prompt, plus the week-long log that led its author to remove it.

Spanish oncology decision-support prototype that walks ESMO guideline trees and uses Jev only for judgment calls.

R&D repo with three Jev pipelines (ticket triage, alert triage, deploy-risk gate) built from four reusable patterns.

Outlook add-in for Microsoft 365 work and school accounts that uses Jev from TypeSafe.

Orchvia: local engine with TS and Python SDKs that runs Claude Code and Codex agents as a team, routing tasks by code and typed decisions.

Self-hosted Rust LLM gateway that puts OpenAI, Anthropic and Jev-style /v1/systemone backends behind one endpoint with load balancing.

Home Assistant integration that turns Jev answers about your house into sensors, automation actions, an AI Task entity and an Assist agent.

Session-aware OpenAI-compatible gateway that routes chat requests by task type, scale and rigor, optionally via Jev Choice questions.

Per-turn router: one ~350 ms Jev call picks model tier, effort, tools and skill, with a hard deadline and regex fallback.

Read-only, local Gmail triage that sorts each message into five trays with an urgency score using Jev via Vercel AI Gateway.

LangGraph decorator that lets Jev take routing decisions it is confident about and falls back to your existing LLM router otherwise.

Chooses the model tier, skills and MCP servers for each coding-agent session with two Jev requests, then launches Claude Code or Codex.

.NET app that classifies Outlook, Gmail and IMAP mail into your categories with Jev, preview-first with a hard cost cap, all local.

Terminal Gmail client for Omarchy where Jev files mail into Gmail labels when confident and grades replies as you write.

Java SDK that lets natural language invoke tinystruct @Action methods, using Jev as a semantic dispatcher with confidence gates.

Filament table filter that scores each row with a Jev Noul on a plain-English statement and keeps rows at or above 0.8.

Vercel Labs example routing form submissions to the right team with Jev via AI SDK, falling back to an LLM when uncertain.

I Ching divination site where charts and verdicts come from code and Jev only classifies the question's topic and screens unsafe ones.

Python library that packs many items into each Jev request for bulk yes/no classification and raises on any unanswered item.

Native macOS launcher and window manager that optionally uses Jev to match loose natural-language commands to known actions.

Gmail organiser where readable rules do most filing and Jev judges only what rules leave, with receipts and undo for every change.

Korean patrol-log tool: upload photos, a general AI reads them and Jev sorts each note into one of four categories for the log.

Self-hosted IMAP mail sorter where a classification model like Jev files new mail into your folders and stars what needs action.

Workbench that turns OpenAI chat requests into Jev state and questions, compares both outputs, and publishes question sets as proxy routes.

Symfony demo that triages French public-service requests with one Jev call each: intent choice, urgency score and bug noul.

Cloudflare Flue agent example that adds a validated route_with_jev tool for typed support routing through AI Gateway.

Async LangGraph example where a Jev Choice labels each email as invoice or general and routes it to a handler.