# navigera

> navigera is browser automation for AI agents from the shell: one native binary (Rust, no Node) that drives Chrome over the DevTools Protocol, one command per step, with pages read as a compact accessibility tree with [ref=N] handles.

Each page below is markdown. The whole site in one file: https://andrey-usa.github.io/navigera/llms-full.txt

## Start

- [Install](https://andrey-usa.github.io/navigera/start/install.md): Every way to install navigera, the platforms it runs on, and which browser it uses.
- [Quick start](https://andrey-usa.github.io/navigera/start/quick-start.md): One session and four commands, from install to a page read.
- [A first session](https://andrey-usa.github.io/navigera/start/tutorial.md): A tour of one session: the page tree and its refs, the commands, naming an element, what comes back.

## Guides

- [Hand the agent your browser](https://andrey-usa.github.io/navigera/guides/your-browser.md): Give an agent your own signed-in browser, a copy of its profile, or a saved state.
- [Drive a browser from a program](https://andrey-usa.github.io/navigera/guides/programs.md): One browser on a pipe with `navigera serve`: one JSON command per line in, one reply out.
- [Use a page's own tools (WebMCP)](https://andrey-usa.github.io/navigera/guides/webmcp.md): Call the tools a page registers for agents through WebMCP, and see which ones it offers.
- [Switch from agent-browser](https://andrey-usa.github.io/navigera/guides/from-agent-browser.md): agent-browser's commands and flags, each with its navigera equivalent.

## Concepts

- [How navigera works](https://andrey-usa.github.io/navigera/concepts/how-it-works.md): The three ways to run navigera; what it does between commands: waits, settling, tabs, dialogs.
- [Supported browsers](https://andrey-usa.github.io/navigera/concepts/browsers.md): Which browsers and engines navigera drives, CI coverage, and how one is found or installed.
- [Lightpanda and your own browser](https://andrey-usa.github.io/navigera/concepts/lightpanda.md): The Lightpanda engine; your own browser, `--attach` and `--profile`.
- [Electron and natural mode](https://andrey-usa.github.io/navigera/concepts/electron.md): Electron apps, `--electron`; `--natural`: a headless run a page cannot tell.

## Reference

- [Commands](https://andrey-usa.github.io/navigera/reference/commands.md): The navigera command line: sessions, flags and output, with the command list by topic.
- [Commands: sessions, tabs and the browser](https://andrey-usa.github.io/navigera/reference/commands-sessions.md): start, batch, sessions, reset, tabs, status, history, profiles, installers.
- [Commands: read the page](https://andrey-usa.github.io/navigera/reference/commands-read.md): goto, the ax tree, text, get, is, eval, find, console, errors, network, locate.
- [Commands: act on the page](https://andrey-usa.github.io/navigera/reference/commands-act.md): click, fill, type and the other actions, wait, downloads, screenshot, pdf, screencast.
- [Commands: state, emulation and audit](https://andrey-usa.github.io/navigera/reference/commands-state.md): cookies, storage, set, route, clock, init-script, WebMCP, passkey, a11y, vitals and totp.
- [navigera --help](https://andrey-usa.github.io/navigera/reference/help.md): The command list exactly as this build prints it.

## Agents

- [For AI agents](https://andrey-usa.github.io/navigera/agents/overview.md): What an agent gets: the skill, the MCP server, and these docs as markdown.
- [Skill](https://andrey-usa.github.io/navigera/agents/skill.md): The guide `navigera install-skill` gives an agent, as this version prints it.
- [Skill references](https://andrey-usa.github.io/navigera/agents/skill-references.md): The detail the skill sends an agent to: acting on a page and reading one.
- [Skill references: inspecting and sessions](https://andrey-usa.github.io/navigera/agents/skill-references-inspecting.md): Inspecting page and browser, state and emulation, and sessions.
- [Skill references: setup and errors](https://andrey-usa.github.io/navigera/agents/skill-references-setup.md): Electron, setup, when something fails.
- [MCP server](https://andrey-usa.github.io/navigera/agents/mcp.md): Run navigera as a Model Context Protocol server for IDE agents, with the setup for each client.

## Benchmarks

- [Results](https://andrey-usa.github.io/navigera/benchmarks/results.md): Every driver and agent tool on the same scripted session, from one CI run, with how each number is taken.
- [Matched operations](https://andrey-usa.github.io/navigera/benchmarks/operations.md): One call per op, warm session, median of 10: navigera against agent-browser, playwright-cli, Playwright MCP, Chrome DevTools MCP and browser-use, each in its default output.
- [Where navigera is not ahead](https://andrey-usa.github.io/navigera/benchmarks/losses.md): Each measure on which another tool beat navigera in the same run.
- [Agent eval](https://andrey-usa.github.io/navigera/benchmarks/agent-eval.md): A generic coding agent, given only the tool and its docs, finishing real tasks: navigera, Playwright, agent-browser.

## Project

- [Changelog](https://andrey-usa.github.io/navigera/project/changelog.md): What changed in each release, and what is on the way.
- [Contributing](https://andrey-usa.github.io/navigera/project/contributing.md): How to build, test, benchmark and release navigera.
- [Source layout](https://andrey-usa.github.io/navigera/project/layout.md): Where each part of navigera lives in the repository.
- [Security](https://andrey-usa.github.io/navigera/project/security.md): What navigera protects and how, its known exposures, and how to report a problem.