ScribePal — Code Forge Temple

ScribePal is an intelligent, open source browser extension that leverages AI to enhance your web experience through contextual insights, efficient content summarization, and smooth interactions. You can find the full source code on GitHub.


ScribePal works with local Ollama models, ensuring that all AI processing and messaging is conducted within your local network. Your private data remains on your system and is never transmitted to external servers. This design provides you with full control over your information and guarantees that nobody outside your network has access to your data.


It is compatible with all Chromium and Gecko-based browsers: Chrome, Vivaldi, Opera, Edge, Firefox, Brave etc.

• AI-Powered Assistance: Interact with locally hosted Ollama models to receive context-aware responses.
• Per-Model Settings: Tune each model individually via the ⚙ icon next to the model selector — enable Thinking for reasoning-capable models, override the sampling Temperature, and set the Context size. Settings are saved per model and shared instantly across every tab and chat box.
• Reasoning Visibility: For models that think out loud, the reasoning streams live into a collapsible panel above the answer, and stays with the conversation so you can expand it again later.
• Context Window Gauge: A colour-coded ring beside the model selector shows how much of the context window your conversation is using, based on the exact token counts reported by Ollama.
• Advanced Capture Tools: Options for capturing text, images and files are available. Captured content is inserted directly into your chat using special tags (@captured-text for text, @captured-image for images, and @attached-files for uploaded files).
• Prompt Customization: Set your own system prompt to shape how a model answers.
• Model Management: Easily select, refresh, download, and delete AI models available on your local Ollama server.

To use ScribePal, ensure that an Ollama server is running on your local network. For more details on setting up your Ollama server, please refer to the detailed instructions in the Prerequisites section.

Reasoning ("Thinking") additionally requires a recent Ollama version and a model that supports it.

1. Install the Extension:
   Install the ScribePal extension from this addons market.
2. Configure the Extension:
   Click on the ScribePal icon in your browser’s toolbar to open the popup. Enter your Ollama server URL and select your preferred theme.
3. Start Chatting:
   Use the draggable chat interface to send your queries and receive AI-generated responses formatted in Markdown.
4. Tune the Model:
   Click the ⚙ icon next to the model selector to adjust Thinking, Temperature and Context size for that specific model.

For more details, please refer to the Usage instructions.


This project is licensed under the GNU General Public License v3.0.