NativeMind
An open-source ChatGPT alternative for Chrome that uses Ollama models locally to chat across tabs, analyze files, and assist with writing.
NativeMind brings a local AI assistant into Chrome for people who want help with webpages, documents, and writing without sending that content to a cloud model. The browser extension connects to Ollama on your machine, keeping prompts and AI processing on-device. It requires no account and uses the AGPL-3.0 open-source license.
Its browser context is a practical reason to choose it over a separate chat window. You can include several open tabs in a conversation, ask for page summaries, or compare information across sites. It also accepts local PDFs, images, and screenshots for questions and analysis.
Agent mode handles requests that need multiple steps, using tools such as file analysis and browser-based web search. Search doesn't depend on an external AI API, though fetching web results still needs an internet connection. Local model use works offline after you've downloaded a model.
For everyday writing, NativeMind can rewrite text, proofread, adjust tone, and help draft Gmail replies. Page translation preserves the layout, with a side-by-side view available for translated text.
Ollama support includes gpt-oss, DeepSeek, Qwen, Llama, Gemma, and Mistral, so you can switch models for different tasks. A WebLLM option runs Qwen3-0.6B directly in the browser through WebAssembly. Developers can also use its in-browser API to send prompts from a web app to their local model.
