ham_home

作者 bingoYB已验证

HamHome is an AI-powered browser extension for browser workspace for bookmarks & tabs: auto-categorization, summaries, semantic search, and secure WebDAV sync. | HamHome 是一款 AI 驱动的浏览器工作空间插件,用于智能管理浏览器书签与标签页工作区,支持智能分类、网页摘要、语义检索与 WebDAV 同步。

112
Stars
6
Forks
TypeScript
语言
2026/8/23
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/bingoYB/ham_home

快速入门

使用 ham_home 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

HamHome

HamHome

AI browser workspace for bookmarks, tabs, sessions, and Agent-assisted extension control

Release Stars Forks Issues License

Product Introduction中文文档Usage中文使用文档FeaturesDevelopment

What is HamHome?

HamHome is a browser extension for turning everyday browsing into an organized, searchable workspace. It combines AI-assisted bookmark saving, a full bookmark library, page snapshots, an Agent that understands and operates HamHome, restorable tab workspaces, and native browser Tab Group automation.

By default, bookmarks, categories, settings, snapshots, vectors, workspaces, and rules live in your browser storage. You can connect your own AI provider for analysis and semantic search, and optionally use WebDAV or export/import files to move structured data across devices.

👉 View Product Introduction - Learn more about the product and download options.

Screenshots

Quick Save PopupBookmark Library
Quick Save PopupBookmark Library
Bulk Bookmark ActionsIn-page Content Panel
Bulk Bookmark ActionsIn-page Content Panel
AI AgentWorkspaces
AI AgentWorkspaces
Tab Group RulesImport, Export, and Sync
Tab Group RulesImport, Export, and Sync

Features

AI-assisted bookmarking

  • Save the current page from the popup, context menu, keyboard shortcut, or in-page panel.
  • Extract page metadata and readable content with Defuddle, Mozilla Readability, and SingleFile-based snapshot capture.
  • Generate summaries, categories, tags, and optional translations after the user configures an AI provider.
  • Re-analyze existing bookmarks in bulk from the management page.

AI Agent and search

  • Search bookmarks by title, URL, description, content, category, tag, domain, and time range.
  • Enable embedding-based semantic search and hybrid ranking that combines keyword and vector results.
  • Use the built-in AI Agent to understand HamHome features and settings, inspect status, search/summarize saved pages, open extension views, and handle safe non-sensitive setup.
  • Search from the browser address bar with the ham omnibox keyword when enabled.

Workspaces and tab sessions

  • Save the current window as a restorable workspace with page order, favicon, pinned state, and native Tab Group metadata.
  • Restore all or selected pages into the current window or a new window, with duplicate URL skipping.
  • Manage workspace-only categories and tags separately from bookmark categories.
  • Analyze workspace pages for duplicates, rough purpose/category signals, and bookmark conversion candidates.
  • Drag pages between workspaces or Tab Groups, edit page metadata, and convert useful pages into long-term bookmarks.

Native Tab Group automation

  • Create automatic grouping rules by domain, URL text, title, case-insensitive title, or regex.
  • Configure group title, color, collapsed state, ordering, and multiple match conditions.
  • Let unmatched tabs fall back to root-domain grouping or AI grouping. Manual rules always run first.
  • AI auto-grouping can use page title, URL, metadata, existing group titles, and custom grouping instructions; results are cached by domain and instruction set.
  • Chromium browsers apply rules through chrome.tabGroups; Firefox can store rules but does not run native Tab Group automation where the API is unavailable.

Snapshots and Obsidian

  • Save local HTML or Markdown snapshots for offline reading.
  • View, download, update, or delete snapshots from bookmark management.
  • Sync Markdown-style bookmark notes to Obsidian through the obsidian://new flow, with clipboard fallback and unchanged-content skipping.
  • Keep snapshot storage visible and manageable from settings.

Import, export, and sync

  • Export full HamHome JSON backups containing bookmarks, categories, workspaces, workspace categories, Tab Group rules, and auto-group settings.
  • Export a browsable HTML bookmark page.
  • Import HamHome JSON backups or standard browser bookmark HTML files from Chrome, Firefox, and Edge.
  • Import browser bookmarks directly through the browser bookmarks API, optionally preserving folder hierarchy or running AI analysis.
  • Write HamHome bookmarks back to the browser bookmark bar with root-folder, clear-first, and duplicate-skip options.
  • Sync structured data through WebDAV under /HamHomeSync: settings, bookmark/category data, bookmark text content, workspaces, workspace categories, and Tab Group configuration. Local HTML/Markdown snapshot blobs stay local unless you export or sync them through the Obsidian workflow.

Privacy and storage controls

  • Store primary data in browser storage and IndexedDB; no HamHome-hosted account is required.
  • Bring your own AI key and endpoint. Supported chat providers include OpenAI, Anthropic, Google Gemini, Azure OpenAI, DeepSeek, Groq, Mistral, Moonshot/Kimi, Zhipu/GLM, Tencent Hunyuan, NVIDIA NIM, SiliconFlow, Ollama, and custom OpenAI-compatible APIs.
  • Configure embeddings separately for semantic search. Supported embedding providers include OpenAI, Google, Azure, Mistral, Zhipu, Hunyuan, NVIDIA, SiliconFlow, Ollama, and custom OpenAI-compatible APIs.
  • Keep sensitive domains out of AI analysis with privacy domain settings and automatic privacy detection.
  • AI keys, Base URLs, privacy domains, WebDAV credentials, and browser shortcuts must be configured by the user; the Agent does not read or fill them.

Modern extension UI

  • Full extension app with bookmarks, categories, tags, workspaces, Tab Groups, import/export, privacy, settings, and about pages.
  • Popup save panel for quick capture.
  • In-page edge-triggered bookmark panel with left/right positioning.
  • Light, dark, and system themes with English and Chinese localization.
  • Sync status widget, shortcut display, custom filters, tag cloud, storage stats, and vector index controls.

Browser Support

BrowserStatus
Chrome / ChromiumManifest V3
Microsoft EdgeManifest V3
FirefoxFirefox build, 109+ configured; native Tab Group automation depends on browser API support

Downloads

Installation from Source

git clone https://github.com/bingoYB/ham_home.git
cd ham_home
pnpm install
pnpm build:extension

Load the built extension:

  • Chrome / Chromium: open chrome://extensions/, enable Developer mode, choose Load unpacked, and select apps/extension/.output/chrome-mv3.
  • Microsoft Edge: open edge://extensions/, enable Developer mode, choose Load unpacked, and select apps/extension/.output/edge-mv3.
  • Firefox: open about:debugging, choose This Firefox, choose Load Temporary Add-on, and select apps/extension/.output/firefox-mv2/manifest.json.

Development

# Install workspace dependencies
pnpm install

# Run extension dev builds
pnpm dev:extension
pnpm dev:ext-firefox
pnpm dev:ext-edge

# Run the Next.js product site
pnpm dev:web

# Build
pnpm build
pnpm build:extension
pnpm build:web

# Package and submit extension builds
pnpm zip:extension
pnpm submit:init
pnpm submit:extension

# Tests and screenshots
pnpm --filter hamhome test
pnpm --filter hamhome test:e2e:install
pnpm --filter hamhome test:e2e
pnpm --filter hamhome screenshots

Tech Stack

Node pnpm TypeScript React

  • Monorepo: pnpm workspaces + Turborepo
  • Extension: WXT + React 19 + TypeScript + Tailwind CSS 4
  • Product site: Next.js 16 + React 19
  • UI: shadcn/ui-style primitives, Radix UI, lucide-react, shared @hamhome/ui and @hamhome/ui-business
  • AI: @browser-agent-sdk/agent, provider adapters, embedding queue, hybrid retriever
  • Extraction: Defuddle, Mozilla Readability, SingleFile-style capture, Turndown/Markdown workflows
  • Storage: WXT Storage, browser storage APIs, IndexedDB for snapshots, AI cache, and vector data
  • Sync: WebDAV, gzip-compressed bookmark content chunks, sync locks, local credential obfuscation
  • Testing: Vitest + Playwright extension E2E + generated screenshot suites

Project Structure

ham_home/
├── apps/
│   ├── extension/          # WXT browser extension
│   │   ├── components/     # React feature components
│   │   ├── contexts/       # Bookmark and app state context
│   │   ├── entrypoints/    # app, popup, content, background entrypoints
│   │   ├── hooks/          # Extension hooks
│   │   ├── lib/            # AI, agent, search, sync, storage, services
│   │   ├── locales/        # English and Chinese i18n resources
│   │   └── e2e/            # Playwright extension tests and screenshot generation
│   └── web/                # Next.js product / marketing site
├── packages/
│   ├── ui/                 # Shared UI primitives
│   ├── ui-business/        # Shared HamHome business UI
│   ├── types/              # Shared TypeScript types
│   ├── utils/              # Shared utilities
│   ├── parser/             # Content parsing package
│   ├── storage/            # Storage abstraction package
│   ├── db/                 # Drizzle schema package
│   ├── api/                # Cloudflare Workers / Hono API package
│   └── i18n/               # Shared i18n package
└── docs/                   # Product docs, Chinese README, screenshots, design notes

Contributing

Contributions are welcome. Please keep changes focused, follow the existing TypeScript and React patterns, and include tests or manual verification steps for extension workflows.

  1. Fork this repository.
  2. Create a feature branch: git checkout -b feature/your-feature.
  3. Commit with a scoped message, preferably Conventional Commits.
  4. Push your branch and open a Pull Request.

License

MIT


If HamHome is useful to you, a star is very appreciated.

常见问题

What is ham_home?

ham_home is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by bingoYB. HamHome is an AI-powered browser extension for browser workspace for bookmarks & tabs: auto-categorization, summaries, semantic search, and secure WebDAV sync. | HamHome 是一款 AI 驱动的浏览器工作空间插件,用于智能管理浏览器书签与标签页工作区,支持智能分类、网页摘要、语义检索与 WebDAV 同步。. It has 112 GitHub stars.

Is ham_home safe to use?

Yes. ham_home passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install ham_home?

Clone the repository with "git clone https://github.com/bingoYB/ham_home" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is ham_home written in?

ham_home is primarily written in TypeScript. It is open-source under bingoYB on GitHub, so you can review or fork the full source.

Are there alternatives to ham_home?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh ham_home against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情