Browser Use's ultrafast agent: Jev picks the operation and DOM element in one request; a small LLM only writes text when typing is needed.
JEV AI 模型开源项目导航
发现基于 JEV AI 模型构建并经过验证的开源项目、SDK、集成与工具。每个收录项目都必须由官方维护,或在项目 README 中提供第一方使用证据。
浏览 JevHunt 无需登录。只有提交公开项目时才使用 Google 登录;JevHunt 绝不会索取你的 Google 密码、JEV API 密钥或付款信息。
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
One AI trade decision every Monad block. Jev on Kuru MON-USDC.
Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos.
Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.
Software Factory Foreman: an agent supervisor that uses Jev decisions to keep coding agents on task.
A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.
A staged code-review workflow and local dashboard built with TypeSafe Jev.
Curated list of official resources and community projects for TypeSafe, System One models, and Jev, with a GitHub Pages site.
Turn any open model into a classifier/jev endpoint
A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.
Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.
Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo.
A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.
Route to the cheapest model in claude code for your task using jev-router
Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.
5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
探索机器原生软件的前沿。
JevHunt 收录基于 JEV AI 模型构建的开源应用、集成与工具。JEV 是 TypeSafe AI 推出的 System One 模型,能够返回带校准置信度的类型化决策。发现生态正在构建的项目,找到合适的仓库,然后开始开发。
█
JEV AI 模型是什么?
TypeSafe AI 的 System One 模型输出决策,而不是大段文字。
决策,而非字符串
Jev 返回软件可直接执行的类型化结果,例如枚举、布尔值和评分整数。无需解析自然语言,也不依赖脆弱的正则表达式。
校准置信度
每项决策都会给出置信度估计。高于阈值时自动执行,低于阈值时交给人工处理。
零幻觉输出
Jev 不生成开放式文本,因此不会编造内容;输出始终限制在调用时声明的模式中。
更像代码
可靠、快速、自洽且类型安全,采用全新架构、采样器以及名为 RLCD 的训练算法。
每一美元的智能,远超常规水平。
浏览 JEV 生态
查找 SDK、集成、工具、应用、实验与研究项目。
开发指南
复制即可使用的常见模式示例。
发布两天内
Jev 刚刚发布。这里记录已经发生的事,以及接下来的计划。
用 Jev 做了项目?
提交到 JevHunt。
目录由社区共同完善。提交应用、模式配方、类型化 Schema 或开源插件,我们会审核并将其收录。