社区开发者基于 MiniCPM5-1B 构建 EdgeHome Harness:全栈 Rust 框架实现智能家居边缘控制器

OpenBMB · @OpenBMB · X·2026-07-03 21:01·60天前
AI 导读

社区开发者 @OrlandoLiuqn 基于面壁智能 MiniCPM5-1B 构建了 EdgeHome Harness——一个全栈 Rust 框架,将轻量 1B 模型转化为可靠的智能家居/垂直场景确定性控制器。整个堆栈仅需 2GB RAM(模型 688MB,运行时约 1GB;Rust Harness 25MB-64MB)。工作流程:用户命令 → MiniCPM5 生成候选 JSON → Rust 验证、规划、执行并追踪,模型从不直接接触设备。框架通过设备注册表与策略门(自动执行/确认/回退)强制安全边界,并内置 Trace/Replay/Eval 实现可观测与可重现。该工程原型证明小模型在合适框架下可可靠运行于边缘。

OpenBMB@OpenBMB
63AI 编辑部评分,满分 100

社区开发者基于 MiniCPM5-1B 构建 EdgeHome Harness:全栈 Rust 框架实现智能家居边缘控制器

2026-07-03 21:01· 60天前
AI 导读

社区开发者 @OrlandoLiuqn 基于面壁智能 MiniCPM5-1B 构建了 EdgeHome Harness——一个全栈 Rust 框架,将轻量 1B 模型转化为可靠的智能家居/垂直场景确定性控制器。整个堆栈仅需 2GB RAM(模型 688MB,运行时约 1GB;Rust Harness 25MB-64MB)。工作流程:用户命令 → MiniCPM5 生成候选 JSON → Rust 验证、规划、执行并追踪,模型从不直接接触设备。框架通过设备注册表与策略门(自动执行/确认/回退)强制安全边界,并内置 Trace/Replay/Eval 实现可观测与可重现。该工程原型证明小模型在合适框架下可可靠运行于边缘。

Big things come in small packages – and MiniCPM5‑1B proves it once again. 🥳 A developer in our community @OrlandoLiuqn built EdgeHome Harness – a full‑stack Rust framework that turns a lightweight 1B model into a reliable, deterministic controller for smart home and vertical scenarios:

⚡ Runs on just 2GB RAM MiniCPM5‑1B (688MB, ~1GB runtime) + Rust Agent Harness (25MB‑64MB) – the entire stack fits comfortably in ultra‑constrained edge devices.

🧠 Model proposes, Harness disposes User command → MiniCPM5 generates candidate JSON → Rust validates, plans, executes, and traces. The model never touches devices directly – every candidate must pass room/device existence, capability checks, and policy gates (auto‑execute, confirm, or fallback).

🛡️ Handles common 1B‑model issues Output Governor handles repetition, rambling, and malformed JSON. Rust manages short‑term memory (last_target, aliases) to avoid context bloat. Device Registry + Policy Gate enforce deterministic security boundaries.

📊 Fully observable & replayable Trace / Replay / Eval make every failure reproducible and measurable – no more tuning by instinct.

This isn’t a commercial gateway – it’s an engineering prototype that proves: small models don’t need to be omnipotent. With the right harness, MiniCPM5‑1B works reliably at the edge. It’s about redefining the model‑system boundary, not cramming cloud AI into tiny boxes.

🔗 Original post: http://zhuanlan.zhihu.com/p/2048065471786886775 GitHub: http://github.com/yushui2022/EdgeHome-Harness