by qybaihe
Provides a coding agent with a judgment kernel that can use Laya as its local judge
mu (μ): a coding agent that thinks before it acts. A small, fast judge makes the routine calls, the big model does the work. Built on pi and AionUi.
Platforms
Use cases
On X
💥厉害了！0.3秒拍板，大模型终于不当保姆了！将Jev深度融合进Harness，让 Jev 和 Laya 兼而得之！ 大模型是发动机，Harness 才是整台车。每一轮对话里那几百个没人认真做的小决定，终于有人接了，本地执行走 Laya，判定又快又稳。 核心亮点： 🔹Jev 接管 35 个判定点：新任务还是纠错、输出哪几块有用、命令是不是你要的、做完验过没有——一次约 0.3 秒，几乎无感。 🔹本地由 Laya 执行：微决策不下放到大模型，本地 Laya 直接拍板，延迟更低、成本更稳 🔹上下文只留这一步：无用技能/MCP 不进场，工具输出逐块过滤，重复日志直接折叠，过期结果直接扔掉 🔹干活和说话拆成两套模型：Jev 挑出真正的新消息，交给会说人话的模型（如 Claude Opus 4.6）讲给你听，人话不污染干活上下文 🔹蜂群中间加闸门：多只「蜂」分头查，Jev 决定说不说、告诉谁、前后对不对得上，把最该传的信息交给最需要它的子 agent 怎么上手： 1️⃣桌面端：macOS / Windows / Linux 直接装 2️⃣命令行：npm i -g mu-agent 3️⃣GitHub： 模型越强，越不该把微决策也扔给它。Jev 进 Harness，本地 Laya 执行，车才真正能开。 #Jev #Laya #Harness #AIAgent #黑客松 #mu #进化酒馆 #TypeSafe #多智能体
Project: mu→Related projects
laya
receptron
Runs Laya typed-decision models from Node.js and TypeScript through ONNX Runtime
typesafe-mcp
itsmostafa
Connects AI agents to typed-decision models through an MCP server
laya-ultrafast
ipenywis
Runs a browser automation agent using local Laya decisions through MLX
FluidUse
FluidInference
Automates form filling on Apple devices with on-device models, including Laya through Core ML
keel
codejunkie99
A macOS coding workspace uses local Laya or hosted Jev to select task routes
laya-typed-decisions
convaiinnovations
A Laya model fine-tuned for agent traces, customer service, invoices, and security incidents
