2026年9月17日 发布的项目

Kev 提供预训练模型和微调功能，可针对共享文本回答是非、单项选择和评分问题。 API 遵循 TypeSafe System One，允许 TypeSafe Python SDK 连接本地 Kev 服务器。

这个 npm 库和 Claude Code 插件通过精简工具调用及结果压缩历史，不改写对话文本。 Jev 分别用 noul 问题判断调用和结果是否应保留，再根据阈值保留、截短或移除配对记录。

模型根据状态与候选项回答选择、布尔和有序评分问题，无需解码回答词元。 NanoJev 是受 Jev 启发的独立本地模型，录像对比包含在同一游戏接口下运行的 Jev 和未微调 Qwen。

TypeLLM 为现有自回归模型添加 JSON Schema 约束输出，无需改变权重或架构。 它受 Jev 启发，同时保留自由文本、可选推理，并支持输出字段间的依赖关系。 用 SGLang 部署兼容模型，再通过 TypeLLMClient 提交上下文和类型化问题。

Foreman 监督编程执行者，评估完成情况、需求满足度、测试充分性及是否需要人工介入。 Jev 评估检查项；确定性的 Python 仲裁器决定继续、引导、验证、停止或升级处理。 提供仓库和任务，并准备 Python 3.11+、TypeSafe 密钥及已配置的编程智能体后端。

Jev Search 将自然语言请求转成网页链接和摘要，提供可编辑筛选与可见的相关性分数。 本地使用时，在 .dev.vars 配置 Search1API 与 Jev 服务商，用 pnpm 安装依赖后运行 pnpm dev。

Jev MCP 为智能体提供证据核查、分类、重排、提取和补丁审阅工具。 使用 Node.js 22 或更新版本，配置 Jev 服务密钥，并在 MCP 客户端注册 npx -y @jkudish/jev-mcp。

Mobile Jev 通过 Mobilerun 控制安卓设备，提供实时工作台、CLI 和执行轨迹。 配置两个服务密钥及已就绪设备 ID，再运行 pnpm dev 打开本地工作台并提交目标。

pg-jev 用自然语言 SQL 条件筛选、排序和分类 PostgreSQL 数据行。 批量 Jev 问题判断各行，SQL 函数返回布尔值、概率、选项或量表评分。 需要 PostgreSQL 14–17、plpython3u、超级用户权限和 TypeSafe 密钥。

jev-voice-browser 将语音转录流发送给 Node 服务，通过 Playwright 控制可见 Chromium 窗口。 Jev 选择意图和目标；代码提取原文候选，并决定执行、等待还是询问。 需要 Node 20+、TypeSafe 密钥，以及 Chrome 或 Edge 麦克风控制页。

System One Connector 通过 evaluate 命令和 MCP 集成向编程智能体提供类型化决策。 可连接 Jev，也可连接 CLM、Laya 等兼容的自托管模型。 定义 Choice、Noul 或 Score 问题，利用提供的智能体配置与批量评估功能。

Unclutter 在 Chrome、Chromium 和 Firefox 中隐藏非必要元素，并为匹配的页面模板保存规则。 Jev 将候选元素分为类型化类别；扩展代码校验响应、控制选择器，并以可撤销方式隐藏内容。 选择 TypeSafe 或 Vercel 凭据，默认手动分析；已保存规则可继续离线使用。

项目将 SGLang 上的 Qwen3.6-35B-A3B 与独立 Python API 进程组合，用于提供类型化决策服务。 POST /v1/systemone 支持 Noul、Choice 和 Score；jev-latest 只是所配置 Qwen 模型的别名。

这个学习项目直接为候选输出评分，回答同一图像的选择、是非和有序评分问题。 这是独立社区对类 Jev 推理的探索，不复现 TypeSafe 的专有架构、训练、校准或服务系统。

Jev Browser 从起始 URL 执行任务，返回最终页面、截图和决策轨迹。 准备 Node.js 22 和 Jev 服务密钥，使用 npm CLI、MCP 服务器或 navigate 库。

Self-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.

Describe your startup idea. Jev decides: kill it, fix it or ship it.

Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.

"Work appears completed or recorded. Run /compact to save tokens."

Live Jev trader on Hyperliquid

A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.

A skill for writing and improving programs that call Jev, TypeSafe's System One model

Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.

Open Jev implementation with custom finetuning

Bounded TypeSafe Jev workflows for coding agents.

Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground

A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.

Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.

Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit

Using Jev as an evaluator.

CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr

Pre-alpha PostgreSQL extension for TypeSafe AI (Jev) categorical classification

🧹 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker.

Ask your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automations, and a conversation agent for Assist.

MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client

mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.

OpenDecision is an open-source semantic decision engine like typesafe's jev.

Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev

Real-time Discord moderation bot: Jev evaluates messages and metadata in parallel to catch phishing, spam, and social engineering with a progressive escalation ladder.

Turn any off-the-shelf LLM into a Jev -like decision layer

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.

Skill for Hermes, and other agents, to ask typesafe's jev

1v1 Jev quickscope arena — Three.js + TypeSafe System One

🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.

Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal)

Classify Git commit diffs and messages with Jev. Bug fixes, security fixes/CWEs, and change types.

An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.

Trading bot with the all new TypeSafe AI's first system one model named as Jev

Batched single-token choice inference for open language models, compatible with TypeSafe

TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer