Version 0.1.9 Developer preview

AI that takes action
in your browser.

Give Nabsun a task. It can navigate websites, click controls, fill forms, and work through multiple steps in your open tabs. You approve actions by default. Use the included local model, connect Codex or Claude, or bring your own AI provider.

Windows x64 and Apple-silicon Mac · About 1.4 GB, including the model

All downloads and installation details

Free and open source. No account needed for the built-in model. Cloud providers have their own account requirements and charges.

Nabsun assistantExample

Page: Service request

Create a service request using these details. Let me review it before submitting.

EXAMPLE AFTER APPROVING THE FORM ENTRIES

I opened the request form, selected the category, entered your details, and reached the review step. Check the entries before approving submission.

Open form → fill fields → review → approve submission

Illustrated examples, not a live assistant. Results depend on your model and the page.

Chromium-based desktop appBookmarks and saved passwordsTabs, downloads, and session restore
BROWSER ACTIONS

Give it a task to carry out

Nabsun can use page controls and check what changed after each action. These are examples to try on supported sites; completion depends on the model, the page, and the permissions you allow.

Work through forms

“Open the support form, choose Billing, and enter the issue details I gave you. Pause before submitting.”

Search and narrow results

“Search for desk lamps, set the price filter to under $50, and open three options in separate tabs.”

Navigate a workflow

“Find the notification settings and turn off the weekly digest.” Nabsun can follow links, change controls, and check the resulting page.

Keep control through approval prompts, allow specific tools, or enable Autopilot for write actions. You handle sign-in, CAPTCHA checks, and protected credential fields.

GET STARTED

From installation to your first task

The first-run guide walks you through setup. You can reopen it in Settings → Getting started.

  1. 1

    Install Nabsun

    Choose your platform’s download. The local model is included, so there is no separate model setup.

  2. 2

    Choose an assistant

    Try the built-in model immediately, or click Connect for Codex or Claude in Extensions → Assistants. Nabsun installs the official CLI if needed and opens provider sign-in. No terminal or npm commands required.

  3. 3

    Describe the task

    Open a website and the assistant. Tell it what to do, such as “Open the contact form and fill in these details.” Review the requested actions and approve them to continue.

MODEL OPTIONS

Choose where your AI runs

Switch models above the chat or in Settings → Model. Codex and Claude have a searchable picker, provider defaults, and custom model IDs. Each provider remembers its selection.

OptionWhat you needWhere it runsUseful for
Built-in Qwen3 1.7B IncludedNo account or API keyOn your CPUSimple questions and basic browser tasks
Codex / Claude CodeConnect in the app and sign in to an eligible provider accountThrough the provider’s CLI and serviceTasks that benefit from a more capable model
OpenAI / Anthropic APIYour API key; provider usage charges applyAt the selected cloud providerChoosing models through your own API account
Ollama / custom local modelYour Ollama server, or a compatible local GGUF model and engineOn the configured machine or serverUsing a local model you already run

Local inference can work offline. Websites and cloud assistants still need internet access. Cloud providers receive the prompts and page context sent to them; model access depends on your account.

PRODUCT DEMO

See the browser and assistant in use

Recorded on an earlier release. The current version adds onboarding, model selection, themes, and update notifications.

The YouTube player loads when you click. Open on YouTube ↗

LATEST RELEASE

What’s new in 0.1.9

Guided onboarding

Choose the built-in assistant, connect a provider, or skip setup and start browsing.

Searchable model picker

Find Codex and Claude models, use the provider default, or enter a custom model ID.

Appearance settings

Classic, Playful, Blossom, and Ocean styles, each with light, dark, or system mode.

Update notifications

Checks at startup and every 24 hours. Check manually in Settings → App updates. Installation is manual.

Also improved: address-bar editing, keyboard navigation, and feedback when settings cannot be saved. Full release notes ↗

DOWNLOAD AND INSTALL

Nabsun 0.1.9

Downloads include the local model and are about 1.4 GB. Verify files against the release’s SHA256 checksums.

macOS · Apple silicon

Download and extract the ZIP, then move Nabsun to Applications. For Macs with Apple M-series chips.

Mac ZIP ↗

Ad-hoc signed, not notarized. macOS may block the first launch. Review the release notes before opening it.

No Intel Mac or Linux installers in this release. All published release assets ↗

BEFORE YOU USE IT

Controls and current limits

Nabsun is a developer preview. Review the assistant’s output and actions, especially before submitting forms or changing account data.

You approve browser actions

Reading pages is automatic. Clicking, typing, navigation, and page code require approval by default. You can allow individual tools or enable Autopilot for write actions. Autopilot stays enabled until you turn it off; page code has its own permission.

Read the security notes ↗

What to expect

  • The small local model can struggle with long or complex tasks.
  • Some websites, sign-in flows, and Cloudflare checks may not work.
  • No private windows, profile sync, tab groups, or split view.
  • Chrome extensions load from folders; there is no Web Store installation flow and API support is partial.
  • Update notifications link to downloads; they do not install updates.
MORE DETAILS

Common questions

Can I use Nabsun from Codex or Claude in my editor?

Yes. Nabsun exposes browser tools through MCP, a protocol that lets AI tools connect to other applications. Copy the connection configuration from Settings → Integrations → Connect an external agent. Calls use the same approval settings as the assistant sidebar.

What data stays on my machine?

The bundled model runs locally, so its inference does not send your prompts to a cloud model provider. Normal browsing still contacts websites, and update checks contact GitHub. If you choose a cloud assistant, it receives the context sent to it. CLI credentials remain in the provider CLI’s store.

Can I give the assistant personal context?

You can edit soul.md with preferences such as your time zone or how you like answers. By default this file is shared only with local models. Settings shows its location and whether it is shared with the selected provider.

How do I report an issue?

Open a GitHub issue with your Nabsun version, operating system, and steps to reproduce the problem. Remove passwords, API keys, and other private information from screenshots or logs.

For developers: build from source

Requires Node.js and npm. These commands install dependencies and fetch the local engine and model. Packaged downloads above do not require these steps.

From source
git clone https://github.com/naveenalavilli/nabsun.git
cd nabsun
npm ci
npm run fetch:model
npm start

If Electron did not download, run npm run setup. Linux requires manual engine setup. See the development instructions.