Setting up
Three short steps, about five minutes in total, with no account, no API key and no cloud service.
- Install: the Mac app, the Windows app or one command installs Browsentic Bridge on your computer, then opens the extension's store page in your browser
- Pair: connect your browser with a single-use code
- First run: a tour of the side panel, and your first instruction
Using it
Features, one page per capability:
| Conversations | Voice, text, one conversation per tab, history |
| Instant commands | Commands that run in the browser in milliseconds, without an agent |
| Page actions | What the agent can do on a page |
| Screenshots | Capturing the viewport, the full page, or one element |
| Theming | Dark mode on any site, and a contrast audit |
| Captchas | What it will and will not do at a "verify you are human" block |
| Monitoring | Watching a long job in the background |
| Site maps | Teaching the agent a site once |
| Recordings | Showing the agent a task once and replaying it later |
| Files | Attaching a file and uploading it to a page |
| Skills | How instructions get routed, and how to write your own |
Configuring
| Choosing an agent | The eight agent CLIs the side panel can run on: switching, and what each needs |
| MCP clients | Optional: registering Browsentic with Claude Code, Cursor, Zed, Codex or Gemini CLI |
| Configuration | Every key in ~/.browsentic/config.json |
| Approvals | Which actions wait for your approval, and how to tune that |
When something is wrong
| Limits | Where Browsentic stops. Read this before relying on it for anything |
| Troubleshooting | Symptom, cause, fix |
| Maintenance | Updating, and removing it cleanly |
How it works underneath: Internals.