WebAgent LabsWebAgent Labs
Features User Manual Privacy GitHub Add to Chrome
← Home

Features & how it works

Everything WebAgent Labs does — and the real agent loop that makes it more than a chat wrapper.

Most AI tools talk. WebAgent Labs works. Every popular AI sidebar is fundamentally a chatbot — it reads what you paste, answers questions about what you describe, and then stops. It can't reach the real browser tab where you're trying to get things done.

WebAgent Labs is different. It perceives the page, reasons about it with an LLM, and takes real actions — clicks, types, navigates, fills forms, even hands-free by voice. It is not a chat wrapper. It is a real agentic AI.

Why WebAgent Labs

Not just another LLM wrapper.

Most "AI sidebars" are ChatGPT inside a panel. They read pages, answer questions, and stop. WebAgent Labs crosses the line into action — and stays open-source, server-free, and yours.

Typical AI Sidebar WebAgent Labs
Reads page content ✓Yes ✓Yes
Chats about the page ✓Yes ✓Yes
Takes real actions on your behalf ✗No ✓Yes — clicks, types, navigates, fills
Hands-free voice control ✗Rare / read-only ✓Speak goals, hear replies, runs actions
Open source — read every line of code ✗Rarely ✓MIT-licensed on GitHub
Free, with a fully on-device option ✗Usually paid ✓Free; Ollama Local = $0
Your data stays on your device ✗Routed via dev server ✓No server exists
Zero telemetry, analytics, tracking ✗Typical ✓None — verifiable in source
Provider freedom (bring your own key) ✗Locked to one LLM ✓8 providers, any model
Agent Mode

Type a goal. Watch the agent finish it.

Give the agent a goal in plain English. It navigates, clicks, types, fills forms, and reports back — across multiple pages and steps — while you watch every action in a live log.

  • Multi-step flows: login, search, filter, checkout, booking, form fill
  • Auto-escalates from DOM to vision when a page deviates from expectation
  • Anti-loop detection: catches its own repetition and changes strategy
  • Pause or stop at any time — you stay in control
WebAgent Labs agent completing a YouTube search task autonomously
Chat Mode

Talk to any web page.

Ask questions about the article, dashboard, or video page you're viewing. Multi-turn conversation with full page context — nothing to configure.

  • ⚡ Text by default — fastest, cheapest. Perfect for articles and plain pages.
  • ✨ Sees when it needs to — a live screenshot is attached automatically on PDFs, visual pages, or visual questions. The model literally sees the layout, charts, and visuals.
  • Works on dashboards, video pages, complex docs — anywhere text alone isn't enough
WebAgent Labs Chat Mode explaining the Hilbert Hotel paradox while viewing a YouTube video
Voice Mode · New

Talk to your browser. It talks back.

Toggle the mic and go fully hands-free. WebAgent Labs transcribes your speech, figures out whether you're chatting or asking for an action, does it, and replies out loud in a warm, natural voice — then goes right back to listening.

1
Listening
Mic is live, capturing what you say.
2
Thinking
Understanding your intent and forming a reply. Mic paused.
3
Working
Running the agent task you asked for. Mic paused.
4
Speaking
Reading the reply aloud, then back to listening.
WebAgent Labs Voice Mode — hands-free conversation bar listening and replying while browsing
Providers · Settings

Your keys, your choice.

Eight providers in Settings, every model field editable — switch any time. Your API keys never leave your device.

  • Pick the right model per role: Agent and Vision
  • Eight providers — Claude, GPT, Gemini, OpenRouter, DeepSeek, Ollama Cloud/Local, or any OpenAI-compatible endpoint
  • API keys stored locally in chrome.storage.local — never seen by us
WebAgent Labs sidebar and settings panel showing eight LLM provider tabs and model fields
Vision Escalation

When DOM isn't enough, the agent climbs.

Most agentic extensions stay at DOM analysis and fail when pages deviate from their assumptions. WebAgent Labs climbs a 4-tier ladder until it gets unstuck.

1
DOM Analysis
Default mode. Fast and token-efficient. Ranks interactive elements.
2
Vision · 80 marks
Screenshot with Set-of-Marks overlay sent to a vision LLM.
3
Vision · 160 marks
Denser overlay for harder pages with many small elements.
4
Raw Coordinates
Last resort: synthetic click at X,Y via the Chrome DevTools Protocol.
Providers

Zero vendor lock-in. Bring your own key, or run fully local.

Eight LLM providers supported out of the box. Every model field is editable so new releases work the day they ship. Use a frontier model where reliability matters; a cheap fast one where speed matters more.

Ollama Cloud FREE TIER Ollama Local FREE OpenAI Anthropic Claude Google Gemini FREE TIER DeepSeek FREE TIER OpenRouter Custom endpoint
Privacy & Security

Local-first. Verifiable. Yours.

There is no developer-controlled server. No telemetry. No analytics. No data sharing with any third party. The local-first architecture is structural, not policy — there is nothing on our side to collect data even if we wanted to.

Stored locally
Settings, API keys, and your current chat — all live in chrome.storage.local, sandboxed per-extension and encrypted at rest.
Your provider, your key
Network requests go only to the LLM endpoint you configure. WebAgent Labs never holds a key on your behalf. Revoke any time on the provider's dashboard.
No remote code
Every line of JavaScript is bundled in the published package. No dynamically-fetched modules. Verifiable by reading the source on GitHub.
Ollama Local = zero egress
Run an LLM on your own machine and no data leaves your device — not to us, not to any cloud. Pure on-device AI.
Limited Use compliant
Adheres to the Chrome Web Store User Data Policy. No advertising. No human reads your data without affirmative consent.
User-initiated only
The agent does not run in the background or wake on a schedule. It acts only when you, the human, give it a goal.

Voice Mode note: text-to-speech runs on your device. Speech-to-text sends microphone audio to your browser's built-in speech service (Google's backend on Chromium) only while Voice Mode is on. WebAgent Labs stores no audio.

Read the full policy: Privacy Policy & Permission Justifications →

WebAgent Labs privacy — local-first settings with your own API keys, no servers and no telemetry

Stop browsing.
Start commanding.

Open-source, under 1 MB, runs on every Chromium browser. Bring your own API key, or run fully local with Ollama.

Add to Chrome — it's free