Token导航 LogoToken导航TokenDH.com
开发敏感数据github未标认证来源可访问许可证需确认审计通过

polpo-cloud波尔波云

Agent Skill

polpo-cloud 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

220

周安装

9

GitHub Stars

公开资料未说明

下载量

71
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:polpo-cloud(波尔波云)
来源仓库:https://github.com/lumea-labs/polpo-skills
仓库路径:skills/polpo-cloud
安装命令:
npx skills add https://github.com/lumea-labs/polpo-skills --skill polpo-cloud
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/lumea-labs/polpo-skills --skill polpo-cloud

简介

用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合围绕仓库状态、代码变更或协作事项进行整理。
  • 可结合来源仓库和原始 README 核验具体用法。
  • 安装命令:npx skills add https://github.com/lumea-labs/polpo-skills --skill polpo-cloud
  • 建议确认权限范围及是否触发联网或文件读写。

SKILL.md

Polpo Cloud CLI

Install

npm install -g polpo-ai

Authentication

# Login via browser (recommended)
polpo login

# Verify
polpo cloud-status

# Logout
polpo logout

Non-interactive login

For CI/CD, scripts, or when browser login is not available, set the POLPO_API_KEY environment variable before running polpo login. Get your key from polpo.sh → API Keys.

export POLPO_API_KEY="..."
polpo login

Do not hardcode API keys in source code or commit them to version control.

Credentials stored at ~/.polpo/credentials.json.

Deploy Agents

Deploy syncs local .polpo/ config to the cloud project.

# From project root (must have .polpo/ directory)
polpo deploy

This uploads:

  • Agent configurations (from polpo.json or .polpo/config.json)
  • Skills
  • Memory

Creates the project automatically on first deploy if none is linked.

Managed AI Gateway

Polpo includes a managed AI gateway with free credits — no LLM key setup needed to get started. Your agents can use any supported model out of the box.

BYOK (Bring Your Own Key)

Optionally set your own LLM provider API keys per project. Keys are AES-256-GCM encrypted at rest.

# Set a key (interactive — prompts securely for the key value)
polpo byok set <provider>

# List keys (masked)
polpo byok list

# Delete a key
polpo byok delete <provider>

Supported providers: openai, anthropic, xai, google, groq, openrouter, cerebras, mistral.

You can also set keys via the dashboard at polpo.sh → LLM Keys. Do not hardcode LLM keys in source code or commit them to version control.

Project Management

# List projects
polpo projects list

# Create a project
polpo projects create my-project

# View cloud project status
polpo cloud-status

Stream Logs

# Stream real-time logs from the project
polpo cloud-logs [--follow] [--tail 50]

Workflow: First Deploy

  1. Sign up at polpo.sh
  2. Create a workspace and project (onboarding handles this)
  3. polpo login (opens browser for approval)
  4. Create .polpo/ directory with agent config
  5. polpo deploy
  6. Use POST /v1/chat/completions with agent: "name" to chat

No LLM keys needed — the managed gateway covers you with free credits.

Dashboard

Available at polpo.sh after signup:

  • Overview: project stats
  • Agents: view/manage agent configs
  • Sessions: chat history with agents
  • Skills: installed agent skills
  • Memory: project + per-agent memory
  • Webhooks: event notification endpoints
  • API Keys: manage data plane keys
  • LLM Keys: BYOK provider keys (optional)
  • Settings: project configuration

API Base URL

  • Cloud: https://api.polpo.sh
  • Local development: http://localhost:3890 (default polpo start port)

See references/cli-commands.md for the full CLI reference.

适合场景

01

调用多模型

02

代码和文本生成

03

Agent 推理流程

04

OpenRouter 模型接入

能力概览

能力 1

统一调用多种 LLM

能力 2

支持 Claude、Gemini、Kimi 等模型

能力 3

适合聊天、代码和推理任务

能力 4

可作为 Agent 模型调用入口

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.51%
按下载量换算26

Claude

29.65%
按下载量换算21

Cursor

19.98%
按下载量换算14

Gemini CLI

9.92%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills