cunzhi

# Cunzhi 🛑 > **The "Premature Termination" Terminator for AI Conversations, Keeping Communication Going** Are you frustrated that your AI assistant always ends conversations prematurely? There’s still so much to discuss, yet it asks, "Is there anything else I can help you with?" **Cunzhi** is here to fix that! When the AI wants to "wrap things up," Cunzhi will promptly pop up a dialog box, allowing you to continue the conversation until the issue is truly resolved. ## 🌟 Core Features - 🛑 **Intelligent Interception**: Automatically pops up continuation options when the AI wants to end the conversation - 🧠 **Memory Management**: Stores development specifications and preferences by project - 🎨 **Elegant Interaction**: Markdown support and multiple input methods - ⚡ **Instant Use**: 3-second installation with cross-platform support ## 📸 See It in Action ### 🛑 Intelligent Interception Popup  *When the AI wants to end the conversation, Cunzhi's intelligent popup appears in time, providing predefined options for quick selection, allowing for deeper communication.* ### ⚙️ Settings Management Interface  *An elegant settings interface that supports memory management, feature toggles, theme switching, and intelligent prompt generation.* ## 🚀 Getting Started ### Method 1: Quick Installation (Recommended) **macOS Users:** ```bash # 3-second installation, no need to wait for compilation brew tap imhuso/cunzhi && brew install cunzhi ``` > ⚠️ **Troubleshooting**: If you encounter a 404 download error, please follow these steps: > > ```bash > # Clear old tap cache > brew untap imhuso/cunzhi > # Reinstall > brew tap imhuso/cunzhi && brew install cunzhi > ``` > > **Common Error Example:** > ``` > curl: (56) The requested URL returned error: 404 > Error: cunzhi: Failed to download resource "cunzhi" > Download failed: https://github.com/imhuso/cunzhi/releases/download/v0.2.0/cunzhi-cli-v0.2.4-macos-aarch64.tar.gz > ``` > > This is usually caused by a version mismatch due to cached previous versions. Clearing the tap and reinstalling will resolve the issue. **Windows/Linux Users:** It is recommended to use Method 2 for manual download, which is simple and quick! ### Method 2: Manual Download 1. Visit the [Releases Page](https://github.com/imhuso/cunzhi/releases) 2. Download the version suitable for your system: - 🐧 **Linux**: `cunzhi-cli-v*-linux-x86_64.tar.gz` - 🍎 **macOS (Intel)**: `cunzhi-cli-v*-macos-x86_64.tar.gz` - 🍎 **macOS (Apple Silicon)**: `cunzhi-cli-v*-macos-aarch64.tar.gz` - 🪟 **Windows**: `cunzhi-cli-v*-windows-x86_64.zip` 3. After extracting, add `Cunzhi` and `Wait a Moment` to your system PATH. ## ⚡ Quick Start ### Step 1: Configure MCP Client Add the following to your MCP client configuration file (e.g., Claude Desktop): ```json { "mcpServers": { "Cunzhi": { "command": "cunzhi" } } } ``` ### Step 2: Open the Settings Interface ```bash # Run the settings command Wait a Moment ``` ### Step 3: Configure Prompts In the "Reference Prompts" tab of the settings interface: 1. View the automatically generated prompts 2. Click the copy button 3. Add the prompts to your AI assistant ### Step 4: Start Using Now your AI assistant has intelligent interception, memory management, and popup interaction features! > 💡 **Tip**: You can refer to the generated prompts for personalized modifications to create a unique AI interaction experience. ## 🔧 Tool Description Cunzhi provides several MCP tools to enhance the capabilities of your AI assistant: - **Code Search Tool**: Semantic code search based on ACE, helping the AI understand the project code structure - 📖 [Detailed Usage Instructions](./ACEMCP.md) ### 🙏 Acknowledgments Thanks to the following open-source projects and their contributors: - **[acemcp](https://github.com/qy527145/acemcp)** - Developed by [@qy527145](https://github.com/qy527145), providing powerful semantic search capabilities for code libraries. This project rewrites the core logic in Rust while retaining the original functionality and integrates it into Cunzhi's MCP tool ecosystem. ## 🤝 Contributing Cunzhi is an open-source project, and we welcome contributions in all forms! ### 🛠️ Local Development ```bash git clone https://github.com/imhuso/cunzhi.git cd cunzhi pnpm install pnpm tauri:dev ``` ## 📄 Open Source License MIT License - Free to use, contributions are welcome!