ChatAI🧠 Local Multimodal AI Assistant Sidebar by ChatAI🧠
A multimodal AI assistant for Firefox powered locally by Ollama. Featuring context-aware menus and custom configuration, it allows you to summarize, translate, or explain web pages and highlighted text, as well as extract text and describe images.
Available on Firefox for Android™Available on Firefox for Android™
13 Users13 Users
Scan the QR code to open this extension in Firefox for Android
Extension Metadata
Screenshots
About this extension
Open-source, private, and local multimodal AI assistant for Firefox: powered by Ollama and OpenAI-compatible endpoints with Vision, Voice, and RAG.
Bring local machine intelligence directly into your Firefox sidebar—completely private, highly configurable, and zero cloud lock-in.
Connect your browser directly to local models to parse images, summarize long documents, write code, and query local context without sending your data to remote servers.
Key Features
100% Private & Local: Connect directly to local Ollama instances or any OpenAI-compatible server. Your prompts, documents, and browsing activity never leave your hardware.
Multimodal Vision: Inspect screenshots, analyze UI designs, and extract text (OCR) via local vision-language models (VLMs).
Contextual RAG: Chat directly with web pages, local documentation, and PDFs using local retrieval-augmented generation.
Voice-Enabled: Dictate prompts naturally with local voice-to-text integration for hands-free workflows.
Developer Workspace: Built-in code block detection, syntax highlighting, one-click copying, and customizable system prompt templates.
Quick Start Guide
1. Install Ollama: Download and install Ollama from ollama.com/download.
Lightweight / CPU-friendly:
$ollama pull minicpm-v
or
$ollama pull lfm3-omni
Balanced performance:
$ollama pull llama3.2-vision
High capability:
$ollama pull qwen2.5-vl
Bring local machine intelligence directly into your Firefox sidebar—completely private, highly configurable, and zero cloud lock-in.
Connect your browser directly to local models to parse images, summarize long documents, write code, and query local context without sending your data to remote servers.
Key Features
100% Private & Local: Connect directly to local Ollama instances or any OpenAI-compatible server. Your prompts, documents, and browsing activity never leave your hardware.
Multimodal Vision: Inspect screenshots, analyze UI designs, and extract text (OCR) via local vision-language models (VLMs).
Contextual RAG: Chat directly with web pages, local documentation, and PDFs using local retrieval-augmented generation.
Voice-Enabled: Dictate prompts naturally with local voice-to-text integration for hands-free workflows.
Developer Workspace: Built-in code block detection, syntax highlighting, one-click copying, and customizable system prompt templates.
Quick Start Guide
1. Install Ollama: Download and install Ollama from ollama.com/download.
- Pull a Multimodal Model: Run one of the following commands in your terminal to grab a vision-capable model:
Lightweight / CPU-friendly:
$ollama pull minicpm-v
or
$ollama pull lfm3-omni
Balanced performance:
$ollama pull llama3.2-vision
High capability:
$ollama pull qwen2.5-vl
- Connect & Launch
Open the sidebar in Firefox, confirm your Ollama host (http://localhost:11434), select your installed model, and begin chatting.
Rated 0 by 0 reviewers
Permissions and data
Required permissions:
- Input data to the clipboard
- Access browser tabs
- Access your data for all websites
Optional permissions:
- Access your data for all websites
Data collection:
- The developer says this extension doesn't require data collection.
More information
- Add-on Links
- Version
- 4.2.0
- Size
- 2.89 MB
- Last updated
- 9 days ago (Nov 10, 2026)
- Related Categories
- License
- Apache License 2.0
- Version History
- Add to collection