3 items
Chat privately with Chrome's built-in Gemini Nano — fully on-device, with chat history, image input, and live diagnostics. LocalChat is a private AI chat that runs entirely inside Chrome. It talks to Gemini Nano — the model built into Chrome itself — through the Prompt API, so every token is generated on your machine. No account, no API key, no server, and nothing you type ever leaves your computer. FEATURES • Clean, familiar chat interface with streaming responses and markdown rendering • Chat history sidebar — conversations are saved locally and restored with full context, including images • Image input — attach, paste, or drag in a picture and ask about it (on devices where Chrome supports multimodal prompts) • Works offline once the model is installed FOR THE CURIOUS • Expandable details under every reply: time to first token, inference time, throughput, chunk telemetry, measured prompt tokens, and per-turn context cost • Diagnostics panel: model availability probes, guided model download with progress, temperature and top-K controls, live session stats, and quick links to Chrome's on-device model internals • A context meter shows how much of the model's window your conversation uses REQUIREMENTS Chrome 138+ with the built-in AI model available. Gemini Nano is a one-time download by Chrome (a few GB) and needs roughly 22 GB of free disk and 16 GB of RAM or a GPU with 4+ GB of VRAM. If the model isn't installed yet, LocalChat walks you through it. PRIVACY LocalChat makes no network requests. Chats, images, and settings are stored only in your browser's local storage. There is no analytics, no telemetry, and no data collection of any kind.
Jul 20, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.