Claw-in-Chrome：在浏览器侧边栏连接自定义 AI 模型的自动化工具

Claw-in-Chrome is a Chrome extension that allows users to connect and use their own AI models directly in the browser sidebar, enabling integrated experiences of web automation, data management, and task execution. It addresses the core limitation of mainstream browser AI assistants—being restricted to vendor-prescribed models—by providing an open, customizable solution.

In recent years, built-in browser AI assistants (e.g., Edge Copilot, Chrome Gemini) have become mainstream. However, these solutions force users to rely on pre-set models, which is a barrier for privacy-focused enterprises, self-hosted model developers, or professionals needing specific capabilities (code generation, multi-language processing). Users often switch between apps/tabs, reducing efficiency.

Claw-in-Chrome's core value is an open, customizable browser AI interface where users can freely choose AI models like search engines. Key features:

1. Multi-model support: OpenAI-compatible APIs, local models (Ollama/LM Studio), self-hosted services (vLLM/TGI), remote servers.
2. Browser automation: Page content extraction, form auto-fill, batch operations, smart navigation.
3. Context-aware dialogue: Current page summary, selected text processing, domain-linked history, multi-modal input.
4. Data management: Clipboard history, Markdown notes, task lists, export to Notion/Obsidian.

Core Components:

• Background Service Worker: Manages persistent AI sessions, cross-tab messages, browser event listening.
• Side Panel: React-based interface for chat, settings, and tools.
• Content Script: Injects into pages for content extraction, automation, and element highlighting.
• Popup: Quick access to toggle sidebar, check status.

Security: Minimal permissions, local data storage, encrypted API keys (via chrome.storage.local), content sandboxing.

1. Researchers: Generate paper summaries, ask deep questions on specific paragraphs, save to Obsidian, batch analyze multiple papers.
2. Developers: Connect internal code models, generate API call examples from docs, run/debug code snippets, copy to IDE.
3. Data Analysts: Extract data via natural language, batch process multiple tabs, export results to CSV/JSON.

Installation:

• Chrome Web Store: Search for "Claw-in-Chrome" and add to Chrome.
• Manual (dev mode): Clone repo, run npm install and npm run build, load unpacked extension in Chrome.

Model Setup Examples:

• OpenAI: Provider=OpenAI, Endpoint=https://api.openai.com/v1/chat/completions, Key=your API key, Model=gpt-4.
• Local Ollama: Provider=Ollama, Endpoint=http://localhost:11434/api/chat, Model=llama3.
• Custom: Provider=Custom, Endpoint=https://your-company-ai.com/v1/chat, Key=enterprise token.

Limitations: Only supports Chrome/Edge, unstable automation on dynamic SPA sites, no mobile support.

Future Plans:

• v1.1: Firefox support, stable automation engine.
• v1.2: Team collaboration (shared prompts, history sync).
• v2.0: Plugin system for third-party extensions.

Claw-in-Chrome offers an open alternative to closed browser AI assistants. It gives users freedom to choose AI models while integrating deeply into browsing workflows, making it ideal for users needing flexible AI service integration in their work.