Gemini-Kchat

Gemini-Kchat is a KDE Plasma plasmoid that integrates Google Gemini AI directly into your desktop. Chat with Gemini using the Google AI Studio API without leaving your workspace.

Features

Core Integration

• Direct integration with Google Gemini AI
• Quick chat interface accessible from your Plasma panel
• Native KDE Plasma integration with system theme support
• Fast and lightweight architecture

Model Support

• Multiple Gemini model selection through dropdown menu
• Supported models:
  • Flash (Latest)
  • Flash-Lite (Latest)
  • Pro (Latest)
  • Gemini 3.6 Flash
  • Gemini 3.5 Flash
  • Gemini 3.5 Flash-Lite
  • Gemini 3.5 Pro
  • Gemini 3.1 Pro Preview
  • Gemini 3.1 Flash-Lite
  • Gemini 3.1 Flash-Lite Preview
  • Gemini 3.1 Pro Custom Tools
  • Gemini 3 Pro Preview
  • Gemini 3 Flash Preview
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • Gemini 2.5 Flash-Lite
  • Gemma 4 (31B, 26B A4B)
  • Deep Research Pro Preview
  • Deep Research Preview (Apr 2026)
  • Deep Research Max Preview (Apr 2026)

Session Persistence

• Save and restore chat sessions across restarts
• Multiple session management with easy switching
• Rename and delete sessions

File Operations

• Gemini can list directories, read files, and write files on your system
• Run shell commands and see the output
• Fully configurable with enable/disable toggle and allowed root directory
• Custom status messages for each operation type

Text-to-Speech

• Multiple TTS provider support:
  • ElevenLabs (cloud, high quality)
  • OpenAI TTS (cloud)
  • espeak-ng (local, fast)
  • Piper (local, neural voices)
  • Speech Note (local, multiple engines via dsnote)
• Audio caching to avoid re-generating

Customization

• Markdown rendering with syntax highlighting for code blocks
• Customizable system prompts
• Full color and theme customization
• Typography options (font family, size)
• Configurable UI elements (buttons, scrollbars, placeholders)
• Custom icon support

Screenshots

Chat interface with markdown rendering and syntax highlighting	Gemini listing directories and reading files with status messages
Running shell commands and writing files directly from chat

---

Installation

Method 1: Using .plasmoid file (Recommended)

1. Download the latest gemini-kchat.plasmoid file from the Releases page
2. Install via command line:

   kpackagetool6 -i gemini-kchat.plasmoid

3. Right-click on your Plasma panel → "Add Widgets..."
4. Search for "Gemini-Kchat" and add it to your panel

Method 2: Manual Installation

1. Download the source code ZIP from the Releases page
2. Extract and install:

   unzip gemini-kchat-vX.X.zip
   cd Gemini-Kchat
   kpackagetool6 -i contents --packageroot ~/.local/share/plasma/plasmoids/ -t Plasma/Applet

3. Right-click on your Plasma panel → "Add Widgets..."
4. Search for "Gemini-Kchat" and add it to your panel

Updating

To update to a newer version:

kpackagetool6 -u gemini-kchat.plasmoid

---

Configuration

Initial Setup

1. Right-click on the Gemini-Kchat widget
2. Select "Configure Gemini-Kchat..."
3. Important: Enter your Google AI Studio API key in the "General" tab
4. Select your preferred Gemini model from the dropdown
5. Customize your agent with colors, typography and interface options

Configuration Options

General Settings & Model Selection	AI Personality Prompt
API key, model selection, file operations and function messages config	Custom system prompt to set Gemini's behavior and personality
Appearance & Colors	Code Block Formatting
Background, message and text color customization for the chat	Syntax highlighting colors for code blocks in responses
Typography	UI Elements
Font family and size settings for the chat interface	Toggle visibility of buttons, scrollbars, and placeholders
Custom Plasmoid Icon	Text-to-Speech
Replace the default widget icon with a custom image file	Multiple TTS providers: ElevenLabs, OpenAI, espeak, Piper, and Speech Note

Note: The widget will not work until you configure your API key. You'll see a reminder message in the chat area if the API key is missing.

Getting Your API Key

To use Gemini-Kchat, you need a Google AI Studio API key (it's free!):

1. Visit Google AI Studio
2. Sign in with your Google account
3. Click "Create API Key" or "Get API Key"
4. Select or create a Google Cloud project
5. Copy the generated API key
6. Paste it in the Gemini-Kchat configuration settings

Important: Keep your API key secure and never share it publicly. The API key is stored locally in your KDE configuration.

---

Usage

Click on the Gemini-Kchat icon in your panel and start chatting with Gemini. Simple as that.

---

Requirements

• KDE Plasma 6.0 or later
• Google AI Studio API key
• For local TTS: espeak-ng or piper (optional)

---

Troubleshooting

⚠️ Rate Limit Errors

If you encounter rate limit errors, make sure you have a valid API key. Generally, API keys work well with the free tier on models like Gemini 2.5 Flash or Gemma 3 27B Instruct. Other models may require billing to be enabled on your Google Cloud project.

---

License

This project is licensed under the GNU Lesser General Public License v2.1 - see the LICENSE file for details.

---

Contributing

Contributions are welcome! Please feel free to submit pull requests, report issues, or suggest new features.

---

Acknowledgments

• Inspired by ChatQT plasmoid by Denys Madureira
• Google AI Studio for providing the Gemini API
• KDE community for the excellent Plasma framework