The open-source browser AI agent: ask about any page, extract data — and, uniquely, transcribe video.
An AI workbench in your sidebar: reads the page, answers questions, structures data into tables — and transcribes video to a transcript in one line. Local-first, your keys, anonymous opt-out telemetry.
Real screen recording (61s): say “transcribe this video” on a Bilibili page → media detected → approve the extraction → local Whisper transcription → timestamped transcript, all in the sidebar.
Two minutes in the sidebar settings — bring your own keys, or go fully local.
Open the sidebar → Settings → Models:
Sidebar → Settings → Models → Speech recognition (ASR):
Then just say “transcribe this video” on any supported page. Full docs: GitHub README
Open any page and talk in the sidebar — read, answer, transform, store. All local-first.
Answers grounded in the live page: summarize long articles, explain content, compare options. Reads first, never makes things up.
Structure page content into tables (CSV download) and markdown notes — searchable and reusable.
MSE sites like Bilibili and Douyin, plus direct links and HLS — say "transcribe this video": the audio track is detected, extracted locally, transcribed with resumable ASR into a timestamped markdown transcript.
Export the whole page as markdown (images localized); data, transcripts, and notes live in one searchable Data tab.
| AutoWeft | Nanobrowser | browser-use | |
|---|---|---|---|
| Page Q&A / understanding | ✓ read-before-answer, verified context | ✓ | ✓ |
| Video/audio transcription | ✓ local extraction + resumable ASR | ✗ | ✗ |
| Full-page markdown export (localized images) | ✓ | ✗ | ✗ |
| Tables → Data tab (CSV) + markdown notes | ✓ | ✗ | ✗ |
| Per-action network authorization (tool+target bound) | ✓ | global or none | — |
| Local-first (media never leaves device) | ✓ | partial | mostly cloud browsers |
| Task reliability (plans / resume / breaker) | ✓ | basic | basic |
| Form factor | Chrome side-panel extension | Chrome extension | Python/TS library |
Comparison based on public features as of 2026-09; file an issue if anything is off.
Media is processed in the browser; agent-initiated network requests need per-action approval. Privacy
No Chrome Web Store yet — the installer writes the build straight into a folder you pick.
Latest:loading… Installed:unknown
· Updates reuse the published file hashes. Unchanged files are checked by size and modification time without reading their contents. Use full check if files appear damaged.
Installation progress
Keep this page open. Do not refresh it or reload the extension while installation is running. Downloading, unpacking and writing can take a little time; wait for the completion message.
The current download is about 20 MB, or 65 MB unpacked. The main files are:
Sizes above are unpacked. Speech model weights are not included; download them separately in extension settings when needed. After unpacking, you can inspect every file’s actual size and purpose.
autoweft-ext).chrome://extensions.Chrome / Edge only (requires the File System Access API).