Launches on September 21, 2026

Two System One models fight a real Doom deathmatch. Laya (322M, open weights, local MLX) vs Jev (TypeSafe hosted). Same state, same typed questions, same shield — only the model differs.

Jev (TypeSafe System One decision model) for DeepSeek Harness: jev_decision, jev_overview, jev_guard_status and jev_verify, structured in-chat tool views, a full settings card, an auto-guard (deterministic + Jev risk/loop) and a /jev dashboard. Real API only, measured numbers.

Fast Memory is an agent memory system built with Jev + LLM.

A verified browser agent: a cheap Jev guard (evidence-checked completions, a destructive gate) in front of any LLM browser driver, with Jev taking the mechanical steps in dual mode. Built on browser-use; every number pre-registered and measured.

A simplified functionality reproduction of Jev-style decisions with Gemma 4. Native multi-modal ability, finetuning free, runs locally on your machine.

Client for TypeSafe's SystemOne API for Jev

JEV 调研报告：TypeSafe System One 决策模型与开源对标（含原始核实记录）

Jev AI agent skill for typed decisions

Makes Claude Code and Codex ask whether a step needs a generative LLM at all — or whether it belongs on Jev, TypeSafe's System One model. Architecture arbitrage before the code is written.

Ten runnable Jev examples for agent decisions: memory conflicts, tool-result checks, recovery, context selection, and handoffs. JavaScript, zero dependencies.

Save LLM calls by letting Codex and other AI agents delegate repetitive computer tasks to Jev.

Watch Jev play Freedoom in a local dashboard. TypeSafe direct and Vercel AI Gateway, inspectable decisions, and bounded spending.

Jev picks what, code owns how - a System One Factorio agent driven by TypeSafe's Jev on FLE

Educational demo: score simulated token launches GEM/RUG via a mocked TypeSafe Jev decision model. Shadow/active router, no real trades.

MCP server wrapping TypeSafe's Jev System One models — typed noul/choice/score judgments for AI agents

Routes prompts to the right Claude tier (Haiku/Sonnet/Opus) using TypeSafe's Jev model

On-call with TypeSafe Jev: the model judges, plain code decides. Root-cause analysis with no LLM in the loop, and alert triage.

Contextual, inline clipboard decomposition for macOS — Tab-to-paste with full history and time-decay ranking. Powered by TypeSafe JEF.

a simulated playground along with actual code samples scenario-based examples

Route any task to the right AI agent in under 1 second using Jev (TypeSafe System One). Supports Claude, ChatGPT, Cursor, and Antigravity with auto-launch on macOS, Windows, and Linux.

Local-first Markdown memory alignment and source-linked search with optional Jev judgments

Pre-message hook: use TypeSafe Jev to keep/drop skills and shrink agent context

MCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server (jev mcp) serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana.

Claude Code + Codex CLI plugin that verifies the agent follows project rules through a System One (Jev) model

Jev and GitHub Copilot harness comparison with a live bilingual ordering dashboard

Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.

Find files by describing them in plain English: find(1) with a semantic --like predicate, answered by TypeSafe.ai's jev model

Metask-Jev: calibrated typed-decision models (Jev-class). Single forward pass, candidate-logit readout. metask-jev-4b beats Bespoke Nimble-9B and Jev on JevBench.

Turn a pile of comments into an auditable distribution: Jev judges each item, code counts the percentages. React workspace + Python engine with pluggable data sources.

Pick a set, state a criterion, let Jev sort it into tiers.

A tinystruct-based TypeSafe SDK with JEV model.

Hands-on demos for TypeSafe's Jev (System One) model: six runnable examples and four field notes. Runs offline with no API key; samples/ holds real measured output from jev-1.13.0.

Unofficial community MCP plugin for Codex and Claude Code using TypeSafe Jev for bounded routing, ranking, extraction, verification, and escalation

Agent Skill and Python workflow for Clay lead scoring, B2B prospect qualification, and people-search ranking with TypeSafe JEV.

Thin clojure wrapper for Jev, TypeSafe AI's classification model

TypeSafe Jev

⚡ DataJev LLM → Analyze Jev → Continue / Switch / Verify / Stop System-1 control for System-2 data agents

One client for every decision model: Choice, Score and Noul over Jev, OpenRouter, laya, MLX, CrossEncoders and LLM fallback

Compile documents, code, SOPs, and resolved cases into evidence-backed JEV judgments, legal actions, guarded adapters, and measured decision systems.

Personal LinkedIn feed labels and ad dimming powered by TypeSafe JEV. Bring your own API key. MIT licensed.

App de escritorio y CLI que puntúa la idoneidad de ofertas de empleo con tu perfil, con análisis y mapa de calor. Electron + Jev.

Microsoft.Extensions.AI provider SDKs: Anthropic Claude and TypeSafe AI Jev

Classify your GitHub stars into GitHub Lists with TypeSafe Jev, and review stars worth dropping

Go client for the TypeSafe System One (Jev) API

Vietnam - Content safety guardrails for AI chatbots: input, output and conversation checks over one policy file with Jev

Judgments from TypeSafe Jev that read like Rust control flow: a yes/no is an if, a choice is an exhaustive match, a score is a comparison.

AI-powered decisions for Magento 2: Jev analyzes orders, customers, products, reviews and abandoned carts and writes the answer right in your admin.

Experimental selective context compaction for Hermes Agent using TypeSafe Jev. Native plugin, local archives, bounded scoring and honest evaluation.

⚡ Browser agent that acts on a hunch: Jev (TypeSafe System One) picks every click in ~150 ms, an LLM is only needed when confidence drops. Zero-dependency Python on top of agent-browser.

Japanese text linter powered by jev (TypeSafe System One)