10 个用 Jev 做决策层的 GitHub 仓库合集
从浏览器 agent、交易循环到代码审查和模型路由，列出 10 个把 Jev 当决策层的开源项目，核心模式是 LLM 生成、agent 执行、Jev 决策。
JEV is getting a lot of attention, but few people know how to actually use it. Here are 10 GitHub repos that show you how: 1. browser-use/jev-ultrafast (~16.6k) Jev for browser agents: pick the next action without another expensive LLM call http://github.com/browser-use/jev-ultrafast 2. tamaratran/fast-jev-compaction (~6.5k) Uses Jev to decide what context still matters and what can be dropped http://github.com/tamaratran/fast-jev-compaction 3. TheoLeeCJ/SemIf (~4k) Open-source Jev-style decision making you can run locally http://github.com/TheoLeeCJ/SemIf-OpenJev 4. jarrodwatts/jev-trader (~2.1k) Real-time trading loop where Jev decides buy, sell or wait http://github.com/jarrodwatts/jev-trader 5. kerpopule/hermes-jev-skills (~670) Jev routing, memory, compaction and skill selection for AI agents http://github.com/kerpopule/hermes-jev-skills 6. devagrawal09/jev-review (~570) Code review powered by Jev decisions instead of one giant prompt http://github.com/devagrawal09/jev-review 7. thruwire/foreman (~520) Jev as a supervisor for coding agents: continue, retry, verify or stop http://github.com/thruwire/foreman 8. superagents-lab/jev-search (~400) Jev decides where and how an agent should search http://github.com/superagents-lab/jev-search 9. droidrun/mobile-jev (~350) Jev for Android agents choosing the next app action http://github.com/droidrun/mobile-jev 10. gargpratyush/jev-router (~340) Routes agent tasks to the right model with Jev http://github.com/gargpratyush/jev-router After going through these, one pattern stands out: LLMs generate, agents execute, and JEV decides. That decision layer is what most agent stacks are still missing Save this post if you want to add JEV to your own workflow.