Launches on September 19, 2026

OMP browser tool that drives any page from one goal using TypeSafe Jev (System One) decisions instead of the main model.

Reproducing the real $1 Chevy Tahoe chatbot exploit and testing 6 AI defenses (incl. TypeSafe's real Jev API) against 36 prompt-injection attacks.

High-speed System One Jev AI decision gateway and MCP server powered by OpenRouter

Open System One model for Apple Silicon: typed decisions with calibrated probabilities from one forward pass.

A command game where the enemy is what people think you meant. Orders in your own words, measured by TypeSafe Jev; officers with doctrine decide.

Open teaching pack for TypeSafe Jev in Grok Bot — three lanes, setup, examples. Gold Hat. No secrets.

Chrome extension: Jev (TypeSafe) tags Outlook Web emails as worth reviewing and categorizes them (PO Variance, Patch Notes, Items, Cost Containment)

Verbatim Jev context compaction for Pi Coding Agent

Single-file pi extension for batched TypeSafe Jev judgments

Pi extension that replaces the built-in LLM compaction summary with TypeSafe Jev's per-tool-call scoring (lossless pruning instead of summarization).

Session-pinned model and thinking selection for Pi using TypeSafe Jev.

Benchmark for Pi skill routing: BM25 vs TypeSafe Jev across roster sizes 50–500

Read-only Linux machine diagnostics using bounded system evidence and AI-assisted analysis.

Every bookmark is a rain check. Find the ones worth redeeming today.

React chess game with TypeSafe Jev AI advisor

Reel Score Lab — pick the best reel. Concept demo UI powered by Jev pilot scores. Not affiliated with TypeSafe.

Agent memory that decides what to hydrate — local topology recall + TypeSafe Jev gates (not another dump-everything store).

jif: calibrated if-statements in R via TypeSafe Jev — judgment-based control flow with reliability curves for biostatistics

An experiment in scoring culture with TypeSafe's Jev

SEAL — No seal, no advance. Workflow kernel: product truth as a sealed graph (not an agent parade, not Jev-with-UI).

竹影 · 原创竹林忍者游戏，支持网页、触屏、Python 桌面和 TypeSafe Jev AI 测试。

🛰 The agent-native blog engine — DSH-Cordis microkernel · 3 GenUI engines · dual-personality theme contract (void × lumen) · Next 16 / React 19 / AI SDK v7. SpaceX space-opera × Apple-minimal.

Turn any open model into a classifier/jev endpoint

Deterministic pre-agent skill routing for Hermes agents: audit, canonical catalog, profile policy, and bounded Jev judgment.

Guideline-driven code review bot for Ruby: code finds what to inspect, TypeSafe Jev judges it, explicit rules decide what to report

Visualize a character's journey through a story using TypeSafe System One

AI coach for Slay the Spire 2 on Steam. Live in-game action recommendations powered by Typesafe Jev through OpenRouter.

Sudoku game played by the TypeSafe Jev decision model through OpenRouter

Reference-track library for critical listening on a summit-fi headphone rig

Portable skills for coding agents: review changes, verify completion claims, and make typed decisions with Jev, local models, or your own server.

A tiny, zero-dependency TypeScript library for Jev by TypeSafe. Checks, classification and scoring, with a live playground.

Tiny demo of TypeSafe System One / Jev: unstructured state in → typed probabilistic decisions out (noul, choice, score). Mock by default; live API optional.

Telegram Goups auditor with TypeSafe models.

A self-organizing Downloads folder. Jev (TypeSafe AI) files each download into the folder you described in plain English; unsure files stay put; every move is logged and undoable.

Engineered with a confluence-driven architecture combining ICT / Smart Money Concepts, a TradingView Chart Pattern Engine, TypeSafe Jev AI (System One) Cognitive Reasoning, Dynamic Leverage (10x–50x), and an interactive Rich Terminal Dashboard UI.

triaje-ambulancias

Guardrails for AI agent actions. Deterministic policy, Jev semantic checks, and replayable decisions.

Typed questions to a model, verdict in code, thresholds from your labels

TypeSafe AI is a San Francisco AI lab building System One models — a class of model trained to return typed, calibrated decisions for software instead of generated text. Its flagship and first System One model, Jev, is served by a single HTTP endpoint: POST /v1/systemone takes a `state` (a string, JSON object, or array) plus a map of typed…

Cache-aware, TypeSafe-driven model tier router for Claude Code

Fail-closed Jev policy gate for Hermes Agent tool calls

Open WebUI pipeline that routes prompts to a cheap or expensive LLM using TypeSafe AI classification

Experimental out-of-tree Kubernetes scheduler plugin that uses TypeSafe's Jev model to produce typed, advisory diagnoses for unschedulable Pods.

Unofficial Go port of the TypeSafe AI SDK

Community Rust SDK for the TypeSafe AI API. A port of the official JavaScript SDK.

Community-built Rust SDK for the TypeSafe AI API (System One / Jev). A port of typesafe-sdk-python

Typed decisions from TypeSafe AI's Jev model inside TYPO3: a decision editor and playground in the backend, powermail_cond operators, and submission routing

Measure meaning by perturbing text and watching a calibrated probability move. Ablation attribution over TypeSafe's Jev, reported against a measured noise floor.

Use jev to classify tags for pages

See what an AI agent actually did, not just its score. Labels every step of a CLI agent's run and compares two rounds against the noise a re-run produces anyway.