Launches on September 21, 2026

JAST is an experimental SAST (static application security testing) desktop app that uses TypeSafe AI's Jev System One model.

Apply natural-language codebooks to tables: a CLI and Python API with resumable annotation, exports, and label evaluation.

Context-aware routing for Codex: classify prompts, choose agent profiles, coordinate subagents, and verify results.

把决策模型 Jev 接进亚马逊广告优化的参考实现：规则层出可追溯结论，Jev 出独立第二意见，分歧即信号。输出可落到飞书多维表格。

Typed-judgment model (TypeSafe Jev) driving task-level decisions on a simulated xArm7: reliability measurements, failure map, sensor-freshness gate

A zero-dependency MCP server for TypeSafe's Jev — calibrated, typed judgments for Claude Code, with a local answer cache and cost tracking.

Finite-sample guarantees for Jev (TypeSafe's System One). Conformal risk control turns calibrated probabilities into certified routing thresholds; prediction-powered inference audits them. 2,412 decisions on CLINC150 for $0.23 — including the shift and prevalence cases where the guarantee breaks.

Using Jev as a chess engine

Highlight text, right-click, Ask Jev — TypeSafe Jev answers in a Chrome side panel

I tested the 'AI model for HFT' hype: TypeSafe Jev on 298,549 intraday trades. 48.4% hit rate, worse than a coin flip before fees. Every model response shipped, so anyone can verify without an API key.

Ask TypeSafe AI typed questions about JSON state from the command line

Semantic code completion for Neovim using Jev (TypeSafe AI) as a ranking oracle. Fuzzy candidates appear instantly; Jev re-ranks them by code context.

An 11-level crash course on Jev, TypeSafe AI's System One decision model — runnable examples against the real API, plus a capstone project with unit tests and evals. Works with any LLM provider via LiteLLM.

Typed semantic creature compilation with Jev: natural language → inspectable genome → deterministic procedural SVG.

Jev-powered technical debt gate for coding agents and CI. Bring your own TypeSafe API key.

LLM input gatekeeper MVP adapted for TypeSafe Jev - jailbreak/injection blocking with calibrated escalation

Comment moderation console adapted for TypeSafe Jev - spam/abuse/borderline routing at ~$20 per million comments

RAG quality gate adapted for TypeSafe Jev - relevance filtering + document injection detection, fan-out in one call

Support-ticket routing MVP adapted for TypeSafe Jev - 100/100 classification with confidence-gated dispatch

JD-anchored resume screener adapted for TypeSafe Jev - swap the job description, flip the verdict

Jev + autonomous driving: structured decisions, multimodal baselines, recovery research, and measured API diagnostics.

Typed decision model judge for GitHub PRs — sub-second, ~$0.0001 per triage (TypeSafe Jev via OpenRouter)

Can you beat Jev at Gomoku, Go or chess? Play TypeSafe's System One decision model on Cloudflare Pages, with every API call shown, a hall of fame and replays.

Small demos + use-case backlog: TypeSafe AI's Jev as a calibrated decision layer for GraphRAG pipelines on Neo4j.

Compose typed Jev judgments as reactive semantic state in React and backend programs

A reproducible benchmark connecting Jev semantic priors with intracortical inner-speech BCI decoding.

A probabilistic, AI-powered utility to determine if a number is not odd (or not even) using TypeSafe's Jev model and the Vercel AI SDK.

Configurable semantic CI checks for repository files using TypeSafe Jev

Lightweight MCP server exposing TypeSafe Jev decision tools via OpenRouter for Hermes Agent

MCP server exposing TypeSafe's Jev typed-decision model over the TypeSafe API or OpenRouter

用 TypeSafe Jev 给 AI coding agent 做持续代码质量 review 的校准审计层。持久化 19 维质量分数，输出趋势矩阵、假阳性置信检测、rubric 漂移与 ECE 校准曲线。Node 22+，零运行时依赖，CLI + GitHub Action，直接消费 jev_review 的 MCP 评估结果。

Mock Jev API decisions with MSW for deterministic tests without real API calls or credits.

Reproducible benchmark evaluating TypeSafe AI's Jev (System One paradigm) on Brazil's ENEM 2025 standardized exam. Evaluates typed decision-making, domain-specific accuracy, and RLCD uncertainty calibration against open LLM baselines with an interactive GitHub Pages dashboard.

Offline-first experiments for abstention and open-world routing with Jev.

Watch TypeSafe's Jev model play browser games live, with the odds of every move on screen.

Jev 决策模型游乐场：斗地主 / 21点 / 数独（纯标准库）+ TypeSafe Mario 真机复现研究

automatically optimizing the instructions and decision criteria of TypeSafe Jev Choice from labeled data

JEV for quilt as understood output: cellular-first decision substrate — typed cells, hook-and-drop deltas, bookkeeper WAL, last-mile projection decoupled

Jev-powered support ticket router — parallel structured decisions via TypeSafe AI

A local-first RSS reader with Jev-powered semantic screening. Follow what matters, inspect every judgment, and keep control of your reading. English / 简体中文.

Benchmark of TypeSafe Jev (System One decision model) for systematic review title/abstract screening vs GLM/Sonnet on Cohen_2006 gold standard

Jev-compatible /v1/systemone server reading typed decisions from LLM logits, benchmarked against TypeSafe's Jev on the same items via JevBench

Claude Code & Codex skills powered by Jev, TypeSafe's System One model. 256 calibrated judgements for $0.0005 in 0.72s — 360x cheaper than Claude Opus 5. Includes the first published Jev calibration curve, measured on 4,995 real agent decisions.

Snake autoplay powered by TypeSafe Jev (System One)

JEV Decision is a live demo that turns market data into structured decisions. It pulls real-time prices, valuation ratios and sector context, then runs a 20-question against TypeSafe Jev model to score buy/sell conviction, financial health and risk

Unofficial Symfony bundle for TypeSafe AI's Jev: typed client, validator constraints, Messenger, Workflow guards and profiler panel

Organize Chrome tabs and groups by meaning with a single Jev API request.

Automated issue & PR triage for open-source maintainers, powered by Jev (TypeSafe AI).

Millisecond-class test-failure triage for coding agents: RETRY / FIX_CODE / FIX_ENV, powered by TypeSafe Jev.

Benchmarks TypeSafe's Jev forecasts against 542 resolved Polymarket markets: Brier score, calibration, and routing tables.