NativeMindExtension

Our little team built a small, open‑source browser extension because I wanted page summary/translate/chat without sending data off‑device. It runs gpt‑oss locally via Ollama. Optional: switch to GPT‑5 if you add an OpenAI API key. Try: 1.Install the extension (GitHub). 2.Install Ollama, then ollama pull gpt-oss. 3.In NativeMind choose “gpt‑oss”, then highlight text or click the toolbar button to summarize/translate/chat. Notes: no backend servers from us; with gpt‑oss everything stays on your machine. With GPT‑5, requests go to OpenAI. Would love feedback on setup friction, performance on your hardware, and missing features. Issues/PRs welcome.

I’ve been experimenting a lot with Ollama and local LLMs lately, and wanted a way to make them useful while browsing — without needing to send anything to the cloud. We tried LM Studio, Mistral via mtsy, and a few other setups — all great in different ways — but Ollama felt the most stable and portable for casual local inference. So our small team built NativeMind, a lightweight open-source Chrome extension that connects to your local Ollama instance and lets you: • Summarize the current page in a sidebar • Ask questions about the content you’re reading • Search across open tabs • Use any Ollama model you’ve got running It runs fully on-device. No external API calls, no accounts, no telemetry. Just local inference in your browser. We mostly use it to speed up reading long-form content (docs, papers, articles), and it’s been surprising

Hi HN, We’ve just launched NativeMind — a fully private, on-device AI assistant browser extension. It runs locally via Ollama and connects to any model you want. So it lives in your browser (currently Firefox and Chromium), works across tabs, supporting workflows like search, summarization, translation, and general Q&A. Note: Still experimenting with broader features. Suggestions are very welcome! Kay