scai/README.md

> AI-powered CLI tools for smart commit messages, auto generated comments, and readme files — all powered by local models.

# ⚙️ scai — Smart Commit AI ✨

> AI-powered CLI tools for smart commit messages, auto generated comments, and readme files — all powered by local models.

**scai** (Smart Commit AI) is a lightweight, privacy-focused CLI tool that uses local AI models (via [Ollama](https://ollama.com)) to help developers work faster and cleaner:

- 🤖 Suggest high-quality Git commit messages  
- ✨ Comments your code automatically
- 🧠 Get a summary of any code file directly to the terminal 
- 🔒 100% local — no API keys, no cloud, no telemetry  

---

## 🚀 Features

- ⚡️ Powered by open local Ollama models like `mistral` and new `commentModule`
- 🛠️ CLI built with Node.js + TypeScript
- 🔒 No external services, full privacy by design  
- ✅ Now supports global options for model and language settings

### 📦 Recent Additions

* **Summary Command**: Print a summary of the given file to the terminal (e.g., `scai summ <file>`)

---

## ❤️ Philosophy: Why Local AI?

We believe your code — and your workflow — should stay **yours**. scai runs entirely on your machine using open-source models and tools.

No internet connection. No vendor lock-in. Just local, private, AI-enhanced developer experience.

✅ Works entirely offline  
✅ No API keys, cloud accounts, or telemetry  
✅ Backed by open-source models  
✅ Designed for CLI-first devs and scriptable workflows  

**scai** follows the Unix philosophy — small, composable tools with powerful output.

---

## 📦 Installation

1. **Install [Ollama](https://ollama.com)**  
   - On **Windows**: [Download Ollama](https://ollama.com/download)  
   - On **macOS**:  
     - Install via Homebrew:  
       ```bash
       brew install ollama
       ```  
     - Or download directly from the [Ollama website](https://ollama.com/download)  
   - Ensure it’s added to your system `PATH`

2. **Install scai globally via npm:**

```bash
npm install -g scai
```

3. **Run the initialization step to start Ollama and install models:**

```bash
scai init
```

This will:
- Launch the Ollama background server (if not running)
- Pull the required models (`llama3`, `mistral`) if they aren’t present

---

## 🧪 Usage Examples

### 💬 Suggest a commit message

```bash
# Stage your changes
git add .

# Let scai suggest a commit message
scai sugg
```

> Example output:
```
feat(api): add error handling to user service
```

To automatically commit with the suggested message:

```bash
scai sugg --commit
```

---

### 🛠 Comment a code file

```bash
scai comment <file>
```

Write comments for the given file. Optional flags:
- `-a, --apply` - Apply the refactored version to the original file

---

### 🔍 Code summary

```bash
scai summ <file>
```

Create a quick summary of the file your working on to gain fast insights. 

---

## 🔐 License & Fair Use

**scai is free to use** for individuals, teams, and companies — including in commercial work.  
You may:

- ✅ Use it internally in your projects  
- ✅ Use it at work or in commercial software development  
- ✅ Share and recommend it to colleagues  

However:

- ❌ You may not **resell**, repackage, or redistribute **scai** as a commercial product or SaaS offering  
- ❌ You may not claim ownership or original authorship  

For full terms, see the [LICENSE](./LICENSE) file.

---