A high-performance streaming Markdown renderer designed for AI command-line tools. Real-time rendering of AI output with syntax highlighting in Markdown format, supporting all mainstream AI CLI tools.

中文README | English README

Temporarily unavailable on Windows, but you can use it in WSL.

• 🚀 Streaming Rendering - Real-time AI output rendering without waiting for complete response
• 🎨 Rich Format Support - Support for headers, lists, code blocks, bold, italic, and all Markdown elements
• 🔧 Universal Compatibility - Support for any AI command-line tool (Gemini, Claude, OpenAI, etc.)
• 📦 Zero Configuration - Transparent parameter passing, no need to adapt different tools
• 🐛 Debug Mode - Built-in debugging functionality for easy troubleshooting
• 🔄 Pipe Friendly - Perfect support for Unix pipe operations
• 🌐 Multi-language - Automatic language detection (Chinese/English)

Ensure you have Rust 1.70+ installed:

# Clone repository
git clone https://github.com/n-WN/aimd.git
cd aimd

# Build
cargo build --release

# Install to system
cargo install --path .

aimd

echo "Explain what Rust programming language is" | aimd

aimd -- gemini --model gemini-2.5-flash -p "Introduce Markdown syntax"

Pipe mode is the most concise way to use, input content will be automatically passed as prompt to default Gemini:

# Simple question
echo "What is machine learning?" | aimd

# File content as input
cat question.txt | aimd

# Multi-line input
cat << EOF | aimd
Please introduce in Markdown format:
1. Python features
2. Common libraries
3. Application scenarios
EOF

Support for any AI CLI tool, just specify the complete command after --:

# Gemini
aimd -- gemini --model gemini-2.5-flash -p "Introduce Rust"

# Claude
aimd -- claude --model sonnet -p "Explain async/await"

# OpenAI
aimd -- openai api chat.completions.create -m gpt-4 --messages '[{"role":"user","content":"Hello"}]'

# Custom tools
aimd -- my-ai-tool --custom-param value "prompt"

Use --debug to view detailed execution information:

# Debug pipe input
echo "Test input" | aimd --debug

# Debug explicit command
aimd --debug -- gemini --help

• Low Latency: Streaming processing, first byte response time < 10ms
• Memory Efficient: Line buffer processing, constant memory usage
• Cross-platform: Support macOS, Linux, Windows
• Zero Configuration: Works out of the box, no configuration files needed

Input Source → PTY Process → Stream Parsing → Markdown Rendering → Terminal Output
     ↓            ↓             ↓                ↓                    ↓
  Pipe/Args    AI Tool      Line Processing   ANSI Coloring      Real-time Display

• PTY Management: Using pty-process to manage pseudo terminals
• Stream Parsing: Custom state machine for Markdown parsing
• ANSI Rendering: Native ANSI escape sequences for coloring
• Parameter Passthrough: Zero-loss parameter passing mechanism

The program automatically detects system language based on environment variables:

• Chinese: When LANG, LC_ALL, or LC_MESSAGES starts with zh
• English: Default for all other cases

Environment variables checked (in order):

1. LANG
2. LC_ALL
3. LC_MESSAGES

# AI Tool Comparison

## Main Features

- **Gemini**: Google's multimodal AI
- **Claude**: Anthropic's conversational AI  
- **GPT**: OpenAI's generative AI

### Code Example

```python
import openai
client = openai.OpenAI()
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Choose the right AI tool based on specific needs

### Rendered Output
![Rendering Example](docs/render-example.png)

## 📝 Development

### Build Requirements

- Rust 1.70.0+
- Cargo

### Development Environment

```bash
# Clone and enter directory
git clone https://github.com/n-WN/aimd.git
cd aimd

# Run tests
cargo test

# Development mode run
cargo run -- --debug -- echo "# Test\n**Bold text**"

# Release build
cargo build --release

aimd/
├── src/
│   └── main.rs              # Main program logic
├── Cargo.toml              # Dependency configuration
├── README.md              # Chinese documentation
├── README.en.md           # English documentation
└── docs/                  # Documentation resources

1. AI tool not found

   # Ensure AI tool is installed and in PATH
   which gemini

2. Permission issues

   # Ensure executable permissions
   chmod +x target/release/aimd

3. Encoding issues

   # Set correct terminal encoding
   export LANG=en_US.UTF-8

1. Use --debug to view detailed information
2. Check if AI tool works normally
3. Verify parameter passing is correct

Contributions are welcome! Please follow this workflow:

1. Fork this repository
2. Create feature branch (git checkout -b feature/amazing-feature)
3. Commit changes (git commit -m 'Add amazing feature')
4. Push to branch (git push origin feature/amazing-feature)
5. Open Pull Request

• Use cargo fmt to format code
• Use cargo clippy for code quality checks
• Add necessary test cases

This project is licensed under the MIT License - see the LICENSE file for details.

• pty-process - PTY management
• Rust Community - Excellent ecosystem
• All contributors and users for their support

• Project Homepage: GitHub
• Issue Reports: Issues
• Feature Requests: Discussions

⭐ If this project helps you, please give us a star!