闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > edge-router
e

边缘路由

技能标识：edge-router

Route AI agent compute tasks to the cheapest viable backend. Supports local inference (Ollama), cloud GPU (Vast.ai), and quantum hardware (Wukong 72Q). Use when an agent needs to decide where to run a task, optimize compute costs, check backend availability, or execute workloads across edge/cloud/quantum infrastructure.

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 1.0.0
检测标记
后台标记通过
免费
免费获取
0
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

边缘路由

边缘路由器

将任务路由到最便宜的可用后端：本地（免费）→ 云GPU（$0.01）→ 量子（$0.10）。

API

基础地址：https://edge-router.gpupulse.dev/api/v1（或 localhost:3825）

路由（推荐）

bash curl -X POST $BASE/route -H Content-Type: application/json \ -d {task_type: inference}

执行（路由+运行）

bash curl -X POST $BASE/execute -H Content-Type: application/json \ -d {task_type: inference, payload: {model: llama3.2:1b, prompt: hello}}

任务类型

  • - inference → 优先本地，云作为后备
  • training → 云GPU
  • quantum → 悟空72Q
  • auto → 最便宜的可用选项

其他

  • - GET /backends — 列表及状态
  • GET /stats — 路由统计
  • GET /health — 健康检查

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 edge-router-1776115956 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 edge-router-1776115956 技能

通过命令行安装

skillhub install edge-router-1776115956

下载

⬇ 下载 edge-router v1.0.0（免费）

文件大小: 1.21 KB | 发布时间: 2026-4-15 12:36

v1.0.0 最新 2026-4-15 12:36
Smart compute routing: local → cloud → quantum

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部