Launches on September 21, 2026

Documentation and Codex skills for code-controlled Jev workflow patterns

Play Chinese Chess (Xiangqi) against Jev - TypeSafe System One decision model as the AI. Score fan-out over legal moves.

Jev (TypeSafe System One) plays Zork I: one Choice per move over Jericho's valid actions, with its confidence on display. French dashboard.

A .NET client library for the [TypeSafe AI](https://typesafe.ai) System One API (`https://api.typesafe.ai`).

A System-1 reflex layer for Claude Code, powered by TypeSafe AI's Jev — route/gate tool calls, verify output, judge completion, and compose decision trees.

通用客服平台:ChatKit UI + Jev 决策 + Qwen 生成 + RAG 知识库 + 插件化 Tools + MCP 数据面,换行业只改 YAML 不改代码

Jev picks, you watch. A hybrid movie recommender: fast semantic + keyword search narrows 4,800 films to a shortlist, then TypeSafe Jev reads your constraints and picks the one film that fits - with a confidence score that decides whether to answer instantly or ask a follow-up.

CLI that filters logs and text by meaning using plain-English yes/no questions and Jev probabilities.

A policy engine for LLM decisions: declare routes, gates and actions once in TypeScript or Python, and every decision comes validated, explainable, replayable and audited.

Jev decision visualisation and debugging panel for coding agents. MCP server + local web timeline, confidence alerts and trace export.

Page truth for browser agents — and decisions that replay, test and audit. Jev picks the element, risky actions are gated, every run replays offline in CI.

JevPolicy is an open-source TypeScript decision runtime that turns probabilistic judgments from Jev, accessed through Vercel AI Gateway, into versioned, deterministic, replayable, observable application decisions.

This is a ping pong game where you compete against jev

PostgreSQL-compatible query language powered by TypeSafe Jev System One models

Run the Laya System One decision model locally behind TypeSafe's Jev wire API, with a demo page

A proof of concept implementation of TypeSafe's Jev API, backed by local Laya checkpoints.

lgtm-dsh is a DSH plugin that automatically installs lgtm, reuses the Jev already configured in DSH, and lets the agent automatically call lgtm during the testing phase.

Use TypeSafe's Jev model to auto-tag the current Obsidian note, picking from the tags you already use.

Ship the result, not the conversation. 35ms discriminative decision engine for AI agent deliverables (inspired by TypeSafe Jev & Occam's razor).

Route Oh My Pi prompts between simple and advanced models with TypeSafe AI's Jev classifier.

A quiet spoiler blocker for YouTube comments. One typed Jev (TypeSafe System One) Noul decision per comment; covered while checked, still covered if the check fails.

JEV x APM progressive-context PoC: TypeSafe System One progressively materializes/dematerializes APM rules and skills

Polymarket resolution-lag scanner built on TypeSafe's Jev model. Finds markets where a published fact already satisfies the written resolution rules but the price has not caught up. Alert-only.

Persistent governance for AI agents — turn Jev judgments into replayable relation state with R2R.

Escribe un tema y mira cómo Jev (TypeSafe) juzga 100 videos de YouTube en segundos. Corre en tu propia cuenta de Cloudflare.

Proof of concept: auto-tagging and triage of Readwise Reader articles using TypeSafe AI's Jev

Resume-to-job-description fit classification using TypeSafe AI's Jev model via LangChain

An autonomous risk-monitoring MCP server. Define a risk profile — a topic, the geographic locations to watch, and the policy triggers that matter — and the server runs an agentic sweep: live web search scoped by a judgment model (Jev), source scoring, and a Markdown briefing you can read from any MCP client.

PT-BR-first, local decision engine for typed decisions at volume.

Find the LLM calls you should move to JEV — scan logs & code for decision-shaped calls, price the migration, calibrate decision models, generate the migration PR. Zero deps, fully local.

Route an agent's intent to the one installed skill that fits, using TypeSafe's Jev

Vendor-neutral SDK for typed decision-making (yes/no, choice, score) — hosted and local

One CLI and Jev-compatible API for local and hosted typed-decision backends (planning)

Every new Chrome tab sorts itself into the right tab group in ~150ms using Jev (TypeSafe). Bring your own key. MV3, no dependencies, MIT.

衆目 / THE HUNDRED EYES — Interactive media art with Jev Choice + Score: one post, 100 fictional perspectives, four amplified voices, then the whole audience.

Tool-agnostic System One decision orchestration skill for AI coding agents, with optional TypeSafe, Jev MCP and CodeGraph integrations.

A security-focused, idiomatic Go client for TypeSafe’s System One API. Community-maintained; not an official TypeSafe SDK.

Research and scaffolding for a TypeSafe Jev MCP server

A type-safe Go SDK for building reliable integrations with strongly typed APIs. Designed to provide an idiomatic developer experience, compile-time safety, and convenient abstractions while reducing boilerplate and preventing common runtime errors.

Typed AI decisions for .NET: ask Jev (TypeSafe AI System One) yes/no, choice and score questions and get a C# enum with calibrated probabilities back.

Turn messy state into typed, auditable classifications, scores, and policy decisions over REST and MCP.

Jev-compatible adapter for vLLM: use any vLLM-served LLM for Choice, Score, and Noul decisions via logprobs—without modifying the model or vLLM service.

Jev for your X. XFlow is a Manifest V3 browser extension powered by Jev, with customizable filtering policies for a cleaner, more personalized X timeline. 专为 X 打造的 Jev。XFlow 是一款由 Jev 驱动的 Manifest V3 浏览器扩展，提供可自定义的过滤策略，助您打造更清爽、更个性化的 X 时间线。

Add as much tabular data as you want to Jev models using adaptive ensembles that learn to query only the rows and columns needed.

Multi-agent healthcare pipeline using Google ADK, stdio MCP tools, and TypeSafe Jev safety gates for instant emergency triage and clinical draft QC.

Record instrumented workflow failures, replay tool traces offline and minimize response fixtures.

Bound agent actions with signed mandates, attenuated delegation and an idempotent budget ledger.

A provider-agnostic policy and authorization layer for AI agents and AI-native applications.

This agi-cli is inspired by hermes by nous research

Node.js bindings for TypeSafe's Jev — the System One model. Typed decisions, probabilities and confidence, with no text generation and no parsing.