Local & offline models

Kev provides pretrained decision models and fine-tuning for yes/no, multiple-choice and rating questions over shared text. Its API follows TypeSafe System One, allowing the TypeSafe Python SDK to target a local Kev server.

The Android assistant reads visible conversations through accessibility and local OCR, displaying analysis and reply suggestions in an overlay. Jev judges intent and response choices; a generative model drafts three candidates and Jev ranks them.

Searchable memory helps recover past decisions, debugging context and feature history across supported coding agents; Markdown remains the source of truth. Optional Jev reranking uses the remote TypeSafe API to reorder memory search results without downloading a local reranker model.

The model answers choice, Boolean and ordered-score questions from states and candidates without decoding answer tokens. NanoJev is a separate local model inspired by Jev; recorded comparisons include Jev and untuned Qwen on the same game interfaces.

Give jevos text or structured state and a yes/no question; it returns the probability of yes. The local server uses Jev's wire format for Noul requests, allowing existing clients to address a separate self-hosted model.

decider returns Choice, Score and Noul probabilities from a state and typed questions in one forward pass. This independent Jev-style model family uses Qwen bases; its training data was not distilled from Jev. Call the Python Decider interface or point TypeSafe SDKs at its compatible local HTTP endpoint.

ollaya downloads named open decision models and serves typed questions through a local daemon. It implements TypeSafe-compatible endpoints for existing Jev clients, while remaining an independent project. Use its CLI, desktop app or MCP server; Modelfiles can package reusable question sets.

awesome-jev-by-typesafe collects sourced Jev use cases, prompts, patterns and starter code as an independent community resource. It explains Choice, Score and Noul for classification, routing and verification while keeping control flow in code. Explore Python and TypeScript examples; offline policy tests need no key, while live examples require TYPESAFE_API_KEY.

LocalJev translates typed decision requests into DiffusionGemma classification prompts and validates the generated probability output. Its Bun service exposes Jev’s response format through a standard OpenAI-compatible chat backend. Run it with Bun and an oMLX server, then direct TypeSafe SDK clients to the local API.

hippo-memory stores agent memories in SQLite, tracks provenance and lets feedback suppress incorrect memories. Its optional Jev reranker orders recalled memories and is disabled by default. Agents can remember and recall through the CLI or MCP, sharing memory across coding tools.

Rizzo Flow runs open decision models locally, returning choices, probabilities, rubric scores and numbers through a Jev-compatible HTTP interface. It reproduces Jev’s interface pattern, not its proprietary architecture or training; the project is independent. Serve a selected model with llama.cpp and point TypeSafe-compatible application code at the local endpoint.

Von scores independent questions in one forward pass for classification, yes/no checks and ordered ratings. It is a separate System One model with a TypeSafe-compatible API, running in-process or through HTTP. Use the Python or TypeScript SDK, or expose the local model with von serve.

Shapeshift turns typed text into event cards, checklists, timers, bill splits and other task-specific interfaces. Optional Jev classifies intent and signals; deterministic code handles dates and arithmetic. Offline keyword classification is the default. Type into the Bun-powered app, choose a card and save it; a server-side TypeSafe key enables Jev.

TipTour is a macOS menu-bar companion with Jev text tasks and a separate Gemini voice mode. Jev chooses locally detected controls; TipTour executes and validates clicks while screenshots stay local. Select a mode, supply its API key and grant permissions; building requires macOS 14.2+ and Xcode.

JevChat-Windows reads WeChat and KakaoTalk conversations with local OCR and offers candidate replies beside the chat window. Jev judges intent and tension and ranks three candidates; a separate language model drafts them. Configure a decision-provider key and a drafting-provider key on Windows 10 1903+ or Windows 11.

Jev Review scans Git diffs or complete codebases for correctness, security, reliability, compatibility and test coverage. Jev selects evidence, classifies mechanisms, scores severity and, when needed, uses Choice to select a reviewer. Code applies thresholds and workflow policy. Use Node.js 24+, Git and a TypeSafe key to generate JSON reports or inspect saved reviews locally.

The package runs Convai Innovations’ Laya model through ONNX Runtime for typed classification and scoring in Node.js and TypeScript. Install @receptron/laya on Node.js 20 or newer, load Laya, then pass state and typed questions to systemOne; close the instance afterward.

The project controls a Minecraft Java 1.16.5 player through Mineflayer, using a separate model for planning and Jev for player actions. Configure the model relay and local runtime paths, install dependencies, start the vanilla server, and launch the documented nether-agent workflow.

Jev Search turns plain-language requests into web links and snippets with editable filters and visible relevance scores. For local use, configure Search1API and a Jev provider in .dev.vars, install dependencies with pnpm, and run pnpm dev.

jev-router launches the native coding CLIs through a local proxy and selects a model tier for each new user turn. Install jev-router with npm, configure JEV_API_KEY, and launch jev-claude or jev-codex with an installed, authenticated upstream CLI.

Mobile Jev controls an Android device through Mobilerun, with a live studio, CLI and execution traces. Configure both provider keys and a ready device ID, then use pnpm dev to open the local studio and submit a goal.

TypeSafe Mario is an experimental NES controller loop using emulator telemetry and RAM-derived game observations. With Python 3.13, a TypeSafe key and your local game setup, inspect state-demo before running the play command.

LLM2Jev scores candidates from local language and vision models using prefill logits without token-by-token generation. It provides an independent Jev-style implementation with a compatible System One HTTP endpoint. Use Python or HTTP with SGLang, Transformers or MLX, including supported text-and-image inputs.

Unclutter hides nonessential elements in Chrome, Chromium and Firefox using saved rules for matching page templates. Jev classifies candidate elements into typed categories; extension code validates responses and controls selectors and reversible hiding. Choose TypeSafe or Vercel credentials and analyze manually by default. Saved rules continue working offline.