Launches on September 18, 2026

Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.

Jev play Tetris in real-time against other AI models

Production TypeSafe Jev (System One) use-case harnesses with confidence-gated decision logic

Block, steer, and "fuzzy lint" with Jev to make agents follow your rules and conventions. CLI, github action, pi package, claude extension, and more. Built with Effect + TypeScript.

Jev-assisted file retrieval and request caching for faster Pi workflows

Unofficial Swift SDK for TypeSafe

Semantic SQL for Postgres, powered by Jev

Pi extension: verbatim context compaction with TypeSafe Jev decisions

pre-commit hook: one Jev call judges whether your commit message matches the diff, plus debug leftovers, scope creep, and a secret belt

Natural-language end-to-end tests for web apps, powered by Jev and Playwright.

unofficial go sdk for typesafe ai. not affiliated with or endorsed by typesafe ai. a side project built to fill the missing go sdk gap, for the community to use.

在 X 的时间线上，给每条帖子标出它想让你干什么。判断来自 Jev，一个只返回概率、不生成文本的模型。

Agent skills for designing, training, evaluating and improving application-specific decision systems. Primitive/model selection, data assembly, export/reload and bounded hill climbing. TypeSafe Jev is the default hosted exemplar; independent of TypeSafe.

Flue agent routing with TypeSafe Jev through Cloudflare AI Gateway

Typed decisions from the shell: an unofficial stdlib-Python CLI and Agent Skill for TypeSafe's Jev model, via the TypeSafe API (default) or OpenRouter. Yes/no, choice and ordinal scores with calibrated probabilities, semantic grep and batch mode.

Minimal grammY Telegram anti-spam bot powered by TypeSafe Jev

RuneBench harness for TypeSafe's Jev: bounded action catalog, tick-mode controller and a live dashboard

Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.

Pokemon Red on PyBoy: code owns the route and the arithmetic, Jev picks at branches in about 100 ms, calibration measured instead of assumed

Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.

Pi extension suite powered by Jev: selective context compaction and model routing

Community Java SDK for Jev, TypeSafe's System One model: typed questions in, typed answers with calibrated probabilities out. Java 17+, Spring Boot starter (unofficial)

Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.

Open-source Codex plugin for TypeSafe Jev decision consultation, failure diagnosis, and evidence-based completion review

Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.

Recursive Jev choice over a taxonomy. Select from more than 255 options without breaking TypeSafe Jev's choice cap.

Neovim: ask the buffer a question, get a quickfix list. Treesitter splits functions, Jev scores each one, probabilities land as virtual text

Jev Studio para criar programas usando Jev da TypeSafe

Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter

Voice-driven semantic auto-advance for Slidev, powered by Cloudflare Agents and TypeSafe AI Jev

Go SDK for the TypeSafe AI API — typed questions in, probability distributions out.

Jev (System One decision model) plugin suite for DeepSeek Harness (dsh)

Local Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlist

Nushell module for the TypeSafe System One API: typed decisions with calibrated probabilities

Code-review gate for CI and coding agents: asks TypeSafe Jev small typed questions about functions, files, tests and docs, and reports findings with locations and probabilities

LlamaIndex reranker + router powered by TypeSafe Jev - typed scores/choices, cheaper than LLM-as-judge.

Model performance first. Token savings second. A Pi extension with freshness-aware read dedupe, Jev log filtering, and searchable verbatim recall. Keeps existing message history intact.

Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev — calibrated probabilities instead of one more opinion.

JevNoiseGate filters unwanted notifications and SMS on Android. Rather than matching keywords, an LLM decides what's noise — and only what it explicitly flags is blocked. Verification codes are matched on-device and never uploaded; anything uncertain passes through.

Idiomatic Java SDK for TypeSafe AI Jev System One decision engine

Compile agent policy prose into deterministic verdict programs: narrow evidence questions for the model, the verdict computed in code. Install: npm i -g jev-compiler

little Jevs helping design and review other Jevs

Record linkage for economists: write the match rule in plain English, get a probability per pair, audit it, cite it. Python, CLI, Stata and R.

Input moderation for Mastra agents on TypeSafe Jev — one file

Jev reads a whole novel in seconds. Every passage becomes a row of colour.

Decision maker for Ruby: turn decision model answers into policy verdicts

Desktop app for paper-trading stocks and crypto on live prices, with TypeSafe's Jev making the calls and your stops, targets and limits enforced in code. Windows and macOS; never touches real money.

Zero-hallucination open-source repo and crate scout powered by TypeSafe AI Jev System One scoring

YouTube sponsor skipper that reads the captions and decides at watch time: a probability heatmap on the seek bar, no crowd database

Jev plays Generation 3 Pokémon via Showdown and a real FireRed ROM.