10 个由 Jev 做决策的 GitHub agent 项目合集
从浏览器操作、代码审查到模型路由与上下文裁剪，列出 10 个把关键决策交给 Jev、LLM 只负责执行的仓库。
this is pure f*cking treasure Opus 5.5 + Jev: 10 GitHub repos where Jev makes every call and your agents just do the work 01 jev-ultrafast ▸ https://github.com/browser-use/jev-ultrafast → a browser agent where Jev picks the action and the exact DOM element, and a separate LLM only types the text 02 mu ▸ https://github.com/qybaihe/mu → a Pi-based coding agent where Jev answers at 38 decision points, like which chunks of a tool output ever reach the context 03 Jevonian ▸ https://github.com/xinyao27/jevonian → a local OpenAI/Anthropic-compatible proxy: one Jev call picks the model and the thinking level for every request 04 pi-warden ▸ https://github.com/DevMortimer/pi-warden → watches your agent for rule breaks, risky actions, stuck loops and fake "done" claims 05 Oko ▸ https://github.com/bartlomein/oko → Jev judges whether each code chunk actually does what the agent asked for, code keeps only the accepted ones and serves them over MCP 06 jev-pref ▸ https://github.com/doeixd/jev-pref → write your project preferences once in jev-pref.json, Jev checks every change against them and feeds the findings back to the agent 07 taste-lint ▸ https://github.com/mblode/taste-lint → catches AI slop in your UI, copy and agent instructions before it ships 08 jev-review ▸ https://github.com/devagrawal09/jev-review → a staged code-review workflow with a local dashboard, every step decided by Jev 09 opencode-jev-orchestrator ▸ https://github.com/aaronshaf/opencode-jev-orchestrator → the parent model stays fixed, Jev spots the hard turns and hands them to temporary subagents 10 yoshi ▸ https://github.com/compozy/yoshi → a Claude Code/Codex proxy where Jev prunes the request context and leaves the tool-call structure untouched Fork any of these Jev builds, then read the full Jev setup below ↓
这条是引用着另一条写的：x.com/hanakoxbt/status/2101709924828934222