Jev ecosystem projects — page 17

弦外之音 —— 微信聊天里的关系进展助手：读屏（无障碍树 / 截屏视觉）→ Jev 判读 + 攻略度 → 聊天模型出 3 条候选回复，攻略度常驻挂在屏幕上。不改微信、不发消息、不注入点击。

Use LLM judgment in regular Elixir control flow.

Evidence-first long-term experiment memory skill for AI coding agents, with optional Jev decision-model layers

安卓无障碍版微信判读：只读屏、只弹 3 条 Toast（意图 / 情绪 / 着急 / 建议），不生成回复文案、不发送 · 零第三方依赖，APK 861 KB

Natural-language constraints for JEPA world-model planning, judged by a decision model instead of an LLM.

A Swift package for typed decisions from language models (probabilities, choices, and scores), with support for local MLX models and the TypeSafe Jev API.

使用 TypeSafe Jev 在 X/Twitter 时间线上识别低质量、垃圾和广告帖子，并在文字区域显示醒目的半透明水印。

Autonomous multi-source rental search powered by TypeSafe Jev

Probabilistic AI decisions as composable backend primitives — typed judgments (noul/score/choice), deterministic thresholds, and explainable workflows. Powered by TypeSafe's Jev, provider-agnostic.

PR Risk review, automated by Jev

Polymarket trading bot driven by Jev (TypeSafe AI) via OpenRouter

J++: an experimental language with standalone source and a Rust runtime. Compose questions and methods. 独立源码，组合问题与方法。

Independent measurements of typed-decision models: Jev (TypeSafe API) vs Laya (open weights), and a local-first cascade that matches Jev's accuracy at 1.8x the speed

星露谷农场小助手：Jev 自主游玩、dsh 插件、独立 CLI 与 SMAPI Mod

A curated list of tools, integrations, and experiments built on Jev, TypeSafe AI's System One model for fast, typed decisions.

⚡ Sub-100ms cognitive reflexes for autonomous coding agents. Powered by TypeSafe AI's Jev & get-fable.

Pi coding-agent extension: TypeSafe Jev checks for tool calls, tool outputs and replies (prompt injection, approvals, secret scrubbing, task pinning)

24/7 market-making system around Jev (TypeSafe System One) decisions: deterministic state, calibrated judgments, hard risk vetoes.

Skip expensive LLM calls when TypeSafe Jev says same intent. OpenAI-compatible local cache proxy — npx @kushalicious/jevcache

Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies.

SLO-aware LLM inference router with Jev decisions, live queue metrics, counterfactual evaluation, and reproducible latency/cost benchmarks

Agent skill for finding, building, evaluating, and improving decision-model systems. Compositional decision calculus, eval harnesses, and bounded prompt/program hill climbing for Software 3.0. TypeSafe Jev is the default hosted exemplar. Independent of TypeSafe.

Flue agent routing with TypeSafe Jev through Cloudflare AI Gateway

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