Claude 浮动助手
Claude 浮动助手 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分，整体质量较高。我们推荐使用将其纳入你的 AI 工具库，帮助提升工作效率。
📚 深度解析
Claude 浮动助手 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。
在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 7.5 分，是同类 Agent 工作流中的精选推荐。
📋 工具概览
Claude 浮动助手 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
📖 中文文档
Claude 浮动助手 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
# 方式一：pip 安装（推荐）
pip install claude-overlay
# 方式二：虚拟环境安装（推荐生产环境）
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install claude-overlay
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/shengyanlin/claude-overlay
cd claude-overlay
pip install -e .
# 验证安装
python -c "import claude_overlay; print('安装成功')"
- 访问 GitHub 仓库获取工作流文件
- 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
- 上传工作流文件
- 按照提示配置必要的环境变量和 API Key
- 运行测试确认流程正常后投入使用
# 命令行使用
claude-overlay --help
# 基本用法
claude-overlay input_file -o output_file
# Python 代码中调用
import claude_overlay
# 示例
result = claude_overlay.process("input")
print(result)
# claude-overlay 配置文件示例（config.yml） app: name: "claude-overlay" debug: false log_level: "INFO" # 运行时指定配置文件 claude-overlay --config config.yml # 或通过环境变量配置 export CLAUDE_OVERLAY_API_KEY="your-key" export CLAUDE_OVERLAY_OUTPUT_DIR="./output"
Claude Overlay
<p align="center"> <a href="https://docs.claude.com/en/docs/claude-code"><img src="https://img.shields.io/badge/powered%20by-Claude%20Code-D97757" alt="Powered by Claude Code"></a> <img src="https://img.shields.io/badge/platform-Windows%2010%20%7C%2011-0078D6" alt="Platform: Windows 10 | 11"> <img src="https://img.shields.io/badge/python-3.10%2B-3776AB" alt="Python 3.10+"> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-3DA639" alt="License: MIT"></a> <a href="https://github.com/shengyanlin/claude-overlay/stargazers"><img src="https://img.shields.io/github/stars/shengyanlin/claude-overlay?style=social" alt="GitHub stars"></a> </p>
### Talk to Claude Code without ever leaving the app you're in — and let it actually see your screen.
<p align="center"><sub><b>Windows 10 / 11</b> only (for now) · runs on your existing Claude subscription — no API key</sub></p>
<p align="center"> <img src="docs/demo.gif" alt="Browsing the Google Cloud AI agent handbook, then summoning the overlay to ask what the page is about — it reads the screen, answers, and offers to translate" width="640"> </p>
Claude Overlay is a frameless, always-on-top chat window that floats over everything you do. Ask a question, and Claude looks at your real screen — every monitor — to answer. No copy-pasting error messages, no describing what you're staring at, no alt-tabbing to a browser. And because it runs the full Claude Code agent under the hood, it doesn't just chat — it can read, edit, and run things for you, right where you work. Point it at the slide deck, document, or spreadsheet you have open and it can change the file you're looking at — you never have to tell it where the file lives or even alt-tab away.
Best of all, it costs nothing extra: it drives your own claude CLI login, so it uses your existing Claude subscription — no API key, no metered billing.
⭐ If a screen-aware Claude that floats over your work sounds useful, star the repo — it helps other people find it.
Prerequisites
You need three things. The included setup.cmd handles #2 and #3 for you — it auto-installs the Claude Code CLI if it's missing and installs the Python packages.
2. Claude Code CLI — installed *and logged in*
The overlay has no brain of its own; it drives the claude command line.
Easiest: just run setup.cmd (below) — it installs the CLI for you with the official native installer if you don't already have it. To install it yourself:
- Native installer — recommended, no Node.js (PowerShell):
irm https://claude.ai/install.ps1 | iex
winget install Anthropic.ClaudeCode). It auto-updates itself. - npm (needs Node.js 18+): npm install -g @anthropic-ai/claude-code
Log in with your own Claude account (Pro/Max subscription — no API key needed): run claude and follow the browser prompt once.
Verify — this must print a version number:
claude --versionInstall
Pick whichever you like — all three end with the overlay ready to run.
🖱️ One double-click — `setup.cmd` (recommended)
Get the repo, then double-click setup.cmd. It checks Python, auto-installs the claude CLI if it's missing (and offers to log you in), and installs the Python packages — so even a fresh machine is one double-click from ready.
git clone https://github.com/shengyanlin/claude-overlay.git⚡ Let Claude install it (if you already have the CLI)
It's an agent — so it can set itself up. With the claude CLI already installed (see Prerequisites), run this from wherever you want it to live:
claude "Set up Claude Overlay for me: clone https://github.com/shengyanlin/claude-overlay, make sure Python 3.10+ is installed (install it if missing), pip install its requirements.txt, then launch it with pythonw. Tell me when it's running."Claude will ask before each step.
Put it on your Desktop (optional)
Double-click Create Desktop Shortcut.cmd to drop a Claude Overlay shortcut — with the orb icon — on your Desktop, so you can launch it like any other app.
Don't just dragStart Claude Overlay.cmdto your Desktop — it's a portable launcher that must stay next toclaude_overlay.py. The shortcut points back to it in place, which is why it keeps working.
---
Configuration
All settings are constants at the top of claude_overlay.py:
- MODEL — defaults to "claude-opus-4-8" (Opus 4.8, 200K context). Append the [1m] suffix for the 1M-context variant (also one click away in the in-app model switcher). Don't use None: the Agent SDK resolves None to an older model, not the CLI's interactive default. - PERMISSION_MODE — "bypassPermissions" by default (see security note below). Use "acceptEdits", "default", or "plan" to add confirmation / read-only. - WORKING_DIR — folder Claude operates in (default: your home directory). - THEME — "light" (warm paper) or "dark". - AUTO_SCREENSHOT_DEFAULT, FONT_SANS/SERIF/MONO, CORNER_RADIUS, ORB_SIZE, HIDE_SCREENSHOT_TOOL, WINDOW_ALPHA — see inline comments.
创新AI工作流工具，值得关注
- 构建多智能体协作系统的 Agent 开发者
- 跨境业务、多语言内容运营团队
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- Python 依赖冲突：建议用 venv / uv 隔离环境
- CLI：直接 npm install -g / pip install，命令行调用
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 构建多智能体协作系统的 Agent 开发者
- 跨境业务、多语言内容运营团队
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- Python 依赖冲突：建议用 venv / uv 隔离环境
👥 适合人群
🎯 使用场景
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
⚖️ 优点与不足
- +MIT 协议，可免费商用
- +大幅减少重复性人工操作
- +可视化流程，清晰直观
- +可扩展性强，支持复杂场景
- −初始配置和调试需投入一定时间
- −强依赖外部服务的稳定性
- −复杂场景需具备一定技术基础
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。
🔗 相关工具推荐
❓ 常见问题 FAQ
经综合评估，Claude 浮动助手 在Agent工作流赛道中表现稳健，质量良好。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。
| 原始名称 | claude-overlay |
| 原始描述 | 开源AI工作流：A floating, screen-aware Claude Code chat for Windows - it reads your screen to 。⭐9 · Python |
| Topics | aiai-assistantalways-on-topanthropicclaudepython |
| GitHub | https://github.com/shengyanlin/claude-overlay |
| License | MIT |
| 语言 | Python |
收录时间：2026-06-04 · 更新时间：2026-06-04 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。