Intent detection with decision models

Tiny JavaScript semantic matcher that classifies text locally in microseconds and escalates ambiguous cases to Jev.

Transparent proxy that asks Jev to classify each coding-agent prompt and injects the decision into the agent's context before it generates.

Ableton Live controller where a one-sentence command in English or Japanese is turned into mixer, transport, clip and device actions.

OpenAI-compatible chat cache proxy that asks Jev or a local System One model whether a new question has the same intent as a cached one.

OpenClaw plugin where Jev decides whether a group-chat bot should reply and, optionally, which model tier should answer.

Japanese System One decision model on ModernBERT-ja (314.6M) returning typed choice, score and bool distributions with no generation.

Local-first desktop and Android attention workbench that extracts deadlines from WeChat and campus notices; Jev optional.

Home Assistant conversation agent that maps Assist commands to built-in intents using a Jev fan-out of typed questions.

Windows tool that reads the local WeChat chat, redacts it, and has Jev judge conversation stage, intent, tension and next action.

Chrome extension tagging each X post's intent (inform, persuade, provoke, sell) plus rage-bait and hidden-ad flags via Jev.

Android WeChat assistant showing Jev emotion probabilities and intent readings beside messages; never sends replies.

TypeScript standard library for System One models: ready-made Jev methods with confidence gates and a turn-by-turn service agent.

Android overlay that reads on-screen chats, uses Jev to judge intent, risk and whether to reply now, then ranks drafted replies.

Local chat analyser that labels each WeChat message's emotion and intent with Jev and grades how your replies landed.

DeepSeek Harness bundle registering a jev_ask tool for typed noul, choice and score questions to Jev.

Home Assistant conversation agent where Jev classifies an utterance and either calls a light, climate or cover service or hands off to Grok.

Self-hosted helper for tricky chats and everyday decisions: Jev makes typed checks, an LLM handles language, the user decides.

Mac voice assistant where one Jev call per utterance maps speech to app, volume, Spotify and system actions; an LLM only answers questions.

Experimental Hono router that matches HTTP requests to plain-language route descriptions using one Jev Noul per route.

Local web and voice interface for Codex and Claude sessions in tmux, where Jev interprets each request and Python performs it.

Web app that reads a two-person chat and labels each message's emotion, intent and reply quality to estimate interest.

Python example classifying customer support messages into 12 intents with Jev, flagging clarification below 0.8 confidence.

Neovim intent router: Jev classifies an AI command as read file, edit code, run command or general question and dispatches it.

Node app that controls Chromium by voice, asking Jev a dozen typed questions per partial transcript to act before you finish.

macOS WeChat helper where an LLM drafts replies and Jev classifies intent, rates risk and ranks the candidates; you press send.

CLI wrapper that, on an unknown subcommand, asks Jev which documented subcommand you meant by intent rather than spelling.

OpenCode plugin collection whose oc-auto-perms package uses Jev to check tool-call intent against natural-language permission rules.

Chinese real-time captioning app where Jev annotates each spoken sentence for key points, emotion and intent as it streams.

Two-tier macOS decision engine: a MiniLM encoder on the Neural Engine decides, escalating unsure cases to Apple's on-device model.

Home Assistant conversation agent that resolves commands from one System One call with a fan-out of typed questions, asking when unsure.