Here is CodeSage v1.0
# CodeSage v1.0 - AI Coding Assistant
I created this AI Coding Assistant as I was unhappy with all the other AI platforms
Now I use my own :-)))
It is 100% cloud based and very cheap to use
best
XARD777

CodeSage is a powerful, GUI-based AI coding assistant powered by **DeepSeek-R1** (Reasoning) and **DeepSeek-V3** (Fast Mode). It's designed for high-speed infrastructure development, code refactoring, and complex problem-solving.
It will remember the last six queries so you can continue the current conversation.
When you click on the New Conversation button you start a fresh query.
Plus it is so easy to upgrade to DeepSeek-V4 when it is released.

---

## Quick Start (The "Antigravity" Way)

If you have **Antigravity** installed, you can skip the manual setup entirely! Just point Antigravity to this folder and say:

> *"Setup CodeSage for me"*

Antigravity will handle the virtual environment, dependencies, and configuration for you in a flash.

---

## Manual Setup Instructions

If you prefer to set it up manually, follow these steps:

### 1. Prerequisites
Ensure you have **Python 3.8+** installed on your system. You may also need the Tkinter library:
- **Linux:** `sudo apt-get install python3-tk`
- **Windows/macOS:** Usually included with Python.

### 2. Clone and Navigate
Download or clone this repository to your local machine:
```bash
cd /path/to/CodeSAGE
```

### 3. Create a Virtual Environment (Recommended)
```bash
python3 -m venv venv
source venv/bin/activate # On Windows use: venv\Scripts\activate
```

### 4. Install Dependencies
```bash
pip install -r requirements.txt
```

### 5. Configure Environment Variables
CodeSage requires a **DeepSeek API Key**. Create a file named `.env` in the project root and add your key:

```env
DEEPSEEK_API_KEY=your_api_key_here
```

*Note: The application also checks `~/.codesage_env` and `/mnt/storage/VAULT-AI/.env` as fallback locations.*

### 6. Launch CodeSage
You can start the application using the provided script:
```bash
./startLAB.sh
```
Or run the Python script directly:
```bash
python3 codesage_v1.0.py
```

---

## Model Modes
- **R1 Reasoning (Default):** Best for complex architecture, logic flows, and deep debugging.
- **V3 Fast Mode:** Best for quick syntax fixes, boilerplate generation, and simple edits.

---

## Troubleshooting
- **No .env found:** Ensure your `.env` file is in the same directory as the script or in one of the fallback locations.
- **Tkinter Error:** On Linux, ensure `python3-tk` is installed.
- **Tiktoken Warnings:** CodeSage will still work without `tiktoken`, but token counting will be less accurate.
Don't worry, Antigravity will install pyton3-tk for you

Remember -- You just need to go to https://platform.deepseek.com/usage and create a new API_KEY for as little as $5
Then add a .env file in VAULT-AI folder and place the DEEPSEEK_API_KEY=your_api_key_here -- inside it and you are good to go.

Again, if anyone improves upon CodeSage feel free to post the upgrade on this thread -- Thank you