浏览器使用 + Jev
Gregor Zunic的动态DOM操作空间航班搜索演示。
A FIELD GUIDE TO JEV / VOL. 01
汇集 Jev 的真实项目、实用指南和来自全网的创意。
Gregor Zunic的动态DOM操作空间航班搜索演示。
01 / A small decision engine. A whole new way to build.
1,195 项资源 / 资源集
SOURCE-LINKED, ALWAYS.AI-assisted summaries and translations. Check original sources for context and performance claims.
Dasheng is a GitHub tool combining speech recognition with Jev for real-time word-by-word transcription and marking of spoken content.
A community post discusses Jev as a faster general classifier/decision-maker, questioning its accuracy in complex scenarios and noting potential benefits in limited solution spaces with low latency requirements.
Compact version of Jev that generates full probability distributions in a single forward pass.
Jev model demonstrates fast decision-making in a strategy game. Achieves high-speed gameplay with minimal visual feedback.
A project using Jev for skill routing in an agent system, based on community development.
A community post listing Chinese open-source Jev clones with technical specifications.
A collection of 19 open-source projects using Jev technology for various applications including AI agents and game interactions.
Testing Jev as a search reranker shows limited improvement over vector retrieval, with mixed results depending on evaluation methods.
A plugin using Jev's scoring capability to remove unnecessary terminal garbage and redundant logs, improving agent performance.
Thread cataloguing the first wave of Jev tools: MCP servers, routers, reviewers, and browser agents.
使用Jev根据用户输入和对话分析选择和更换服装的实时虚拟试穿实验。
Jev使用快速推理和结构化输出控制超级马里奥兄弟,展示其在实时应用中的潜力。
浏览器使用中的超快速代理:Jev在一次请求中选择操作和DOM元素;仅当需要输入时,小型LLM才编写文本。
将JSON渲染与Jev结合的实验,用于快速生成用户界面,实现组件和设计系统的快速渲染。
从 API 密钥到类型化决策的最短路径。
Claude代码插件通过Jev决策替换压缩摘要,通过一次快速请求对每个工具调用和结果进行评分,过时的调用会被丢弃或截断,所有保留的内容保持原样。
演示Jev在Higgsfield上为视频和图像生成任务选择最合适的AI模型。
实时评估提示难度的分类器,可为简单提示启用快速模式以提升用户体验。
MOSS根据指令捡起垃圾的模拟,旨在通过自动化决策提高街道清洁度。
为软件而非对话构建的机器原生智能的主张。
发布文章:架构、RLCD 训练、定价、Doom 和 Wikiracing 演示、常见问题。
POST /v1/systemone 的请求和响应协议。
const answer = await client.systemOne({
state, questions
});
// intelligence, in your code.官方同步和异步 Python 客户端。pip install typesafe-sdk。
粘贴一个状态,添加问题,并在浏览器中查看类型化答案。