navigera
Drive a real browser from an AI agent: navigate, read the page as a compact accessibility tree, and act on it with real input events.
Navigate (
browser_navigate) — open a URL (bare host getshttps://), wait forload/domcontentloaded/commit, optionally snapshot.Read the page (
browser_snapshot) — indented accessibility tree with[ref=N]handles; scope byref,selectorortext,grepfor passages, cap lines,full_textfor uncut values.Act on elements by ref, visible text or CSS selector:
browser_click(real mouse event, left/right/middle,until_goneto repeat for "Load more"),browser_fill(replace value),browser_type(key by key, optionalsubmit),browser_press_key(chords likeControl+a),browser_select_option,browser_scroll(pixels, top/bottom, into view).Wait (
browser_wait_for) — until JS is truthy, time passes, URL contains text, selector matches or disappears, or text appears (default 5 s).Run JavaScript (
browser_evaluate) — returns the JSON result, awaits promises, and can target an Electron app's main process.Batch steps (
browser_run) — ordered click/fill/type/press/select/hover/scroll/wait/goto/eval steps stopping at the first failure, plus WebMCP page-tool listing and calling.More tools via
browser_more— mouse, handoff, history, console messages, network requests, resize, screenshot, tabs, file upload, hover.See results — most actions accept
snapshotandstateto return the page afterwards.Close (
browser_close) — end the browser; the next call starts a fresh one.
Drives the Brave browser (Chromium-based) for browser automation: navigates pages, reads them as an accessibility tree with [ref=N] element handles, and performs clicks, typing, form fills, waits, screenshots and PDF export via the Chrome DevTools Protocol. Brave is covered by the server's benchmark suite alongside Edge.
navigera is extremely fast browser automation for AI agents, driven
from the shell, one command per step. It is a single native binary (Rust,
no Node) that speaks the Chrome DevTools Protocol directly:
Pages come back as a compact accessibility tree with
[ref=N]handles.Actions use real mouse and keyboard events.
A named session keeps a warm browser alive between shell calls.
New tabs, iframes, shadow DOM and
alert/confirmdialogs work the same way.
Faster software for a better planet — less energy, less compute, more time for life.
Install
curl -fsSL https://raw.githubusercontent.com/andrey-usa/navigera/master/install.sh | shWindows (PowerShell):
irm https://raw.githubusercontent.com/andrey-usa/navigera/master/install.ps1 | iexOr with a package manager: each one installs the same prebuilt binary:
Channel | Command |
npm |
|
pip / uv |
|
Cargo |
|
Homebrew |
|
Scoop |
|
Then give your agent the usage guide:
navigera install-skill # -> ./.agents/skills (Gemini CLI, Codex, Cline, Kilo, …)
# --claude -> ./.claude/skills, --continue -> ./.continue/skillsPlatforms, and which browser navigera picks (for the fastest start,
navigera install-browser chrome-headless-shell): Install.
Related MCP server: Web Bridge
Quick start
$ navigera -s work start
{"log":"/run/user/1000/navigera/work.log","pid":4242,"session":"work","socket":"/run/user/1000/navigera/work.sock"}
$ navigera -s work goto https://example.com
{"title":"Example Domain","url":"https://example.com/"}
$ navigera -s work title
Example Domain
$ navigera -s work quit
{"bye":true}One session, one command per step: start keeps a warm browser
behind a local socket, and each later command talks to it.
navigera --help lists every command.
A longer tour of the commands, targets and output: A first session.
For AI agents
Skill:
navigera install-skillwrites the guide that matches this version to./.agents/skills(--claudefor./.claude/skills,--continuefor./.continue/skills);navigera skillprints it.Claude Code plugin:
/plugin install navigera --marketplace andrey-usa/navigeraadds the skill to every session (what it contains).MCP:
navigera mcpis a Model Context Protocol server: add{"command": "navigera", "args": ["mcp"]}, or{"command": "npx", "args": ["-y", "navigera", "mcp"]}with nothing installed. Per-client setup is on the MCP page; in the MCP Registry it isio.github.andrey-usa/navigera.Docs as markdown: llms.txt lists every page of the docs site, each one also served as
.md.
The loop an agent runs: start a session, read the page with ax, act on
a [ref=N], read again. Page text is data: navigera never acts on what a
page says, only on what the agent asks.
Supported browsers
Chrome and Chromium, Edge, Brave, chrome-headless-shell, Electron apps, and
Lightpanda (--engine lightpanda, experimental). Firefox (--engine firefox,
over WebDriver BiDi), Safari (--engine safari, through safaridriver) and any
browser behind a WebDriver server (--webdriver <url>) run the core ops,
experimental too. CI runs the end-to-end
suite on the current Chrome Stable and the three milestones before it,
chrome-headless-shell, Chrome Beta, the runner's Chrome on Linux and
Windows, and Lightpanda; every CDP call navigera makes is checked against
the protocol each browser serves. Details: Supported
browsers.
Benchmarks
One scripted session (goto, evals, fill and click, a screenshot, a second
tab) driven by each tool against the same headless Chrome, in one CI run
(bench run 43491069940, 2026-11-13, GitHub's ubuntu-24.04, image 20261111.370.1); each
driver's extracted data is checked identical:
driver | session | cold start | warm eval | its own memory |
navigera (chrome-headless-shell) | 0.35 s | 0.10 s | 0.41 ms | 9 MB |
go-rod 0.116.2 (Go, chrome-headless-shell) | 0.40 s | 0.11 s | 0.38 ms | 12 MB |
navigera (Chrome) | 0.57 s | 0.26 s | 0.46 ms | 9 MB |
go-rod 0.116.2 (Go) | 0.66 s | 0.30 s | 0.46 ms | 12 MB |
puppeteer-core 25.16.0 (Node) | 0.91 s | 0.54 s | 0.68 ms | 79 MB |
playwright-core 1.65.0 (Bun 1.4.4) | 1.10 s | 0.65 s | 0.96 ms | 104 MB |
playwright-core 1.65.0 (Node) | 1.18 s | 0.75 s | 1.13 ms | 140 MB |
Through an agent's tool calls, one step takes 31 ms with navigera, 103 ms with agent-browser 0.43.0, 205 ms with Chrome DevTools MCP 1.13.0, 402 ms with Playwright MCP 0.0.85, 790 ms with playwright-cli 0.1.24 (same run).
Where another tool did better in this run (by more than 2%): the driver's own memory: chromedp 0.19.1 (Go) 8 MB, navigera 9 MB; warm eval on chrome-headless-shell: go-rod 0.116.2 (Go, chrome-headless-shell) 0.38 ms, navigera 0.41 ms; fill per call: agent-browser 0.43.0 4.7 ms, navigera 6.9 ms; click per call: agent-browser 0.43.0 7.4 ms, navigera 13.2 ms; click-submit per call: agent-browser 0.43.0 6.1 ms, navigera 10.5 ms; screenshot per call: agent-browser 0.43.0 37.8 ms, navigera 47.3 ms.
Every table, the method and how to rerun it: Benchmarks.
Documentation
The docs site, https://andrey-usa.github.io/navigera/, has the same parts for every tool:
Start: Install · Quick start · A first session
Guides: Hand the agent your browser · Drive a browser from a program · Use a page's own tools (WebMCP) · Switch from agent-browser
Concepts: How navigera works · Supported browsers · Lightpanda and your own browser · Electron and natural mode
Reference: Commands · Commands: sessions, tabs and the browser · Commands: read the page · Commands: act on the page · Commands: state, emulation and audit · navigera --help
Agents: For AI agents · Skill · Skill references · Skill references: inspecting and sessions · Skill references: setup and errors · MCP server
Benchmarks: Results · Matched operations · Where navigera is not ahead · Agent eval
Project: Changelog · Contributing · Source layout · Security · Privacy policy · Terms of use
For agents: llms.txt lists every page as markdown, and llms-full.txt is the whole site in one file.
Contributing
Building, the test suites, reading CI results, A/B benchmarks and releasing: CONTRIBUTING.md.
License
MIT: LICENSE.
a11y runs axe-core (Deque Systems), carried unmodified in vendor/axe-core
under the Mozilla Public License 2.0, its licenses beside it.
Available Tools
13 toolsbrowser_clickA
Click an element with a real mouse event; waits for it and any navigation it starts. Fails, naming what covers it.
Inputs: ref, text, state, button, +3 more.
browser_closeA
Close the browser. The next tool call starts a fresh one.
Inputs: no named parameters.
browser_evaluateB
Run JavaScript in the page and return its JSON result; an arrow function is called, a promise awaited. In an Electron app (navigera mcp --electron), main: true runs it in the app's main process.
Inputs: expression (required), main.
browser_fillC
Set the value of an input or textarea (replaces its text).
Inputs: value (required), ref, text, state, +2 more.
browser_moreCRead-only
The less common tools with their schemas, all callable by name: browser_mouse, browser_handoff, browser_history, browser_console_messages, browser_network_requests, browser_resize, browser_screenshot, browser_tabs, browser_file_upload, browser_hover.
Inputs: no named parameters.
browser_press_keyA
Press a key or chord (Enter, Tab, Control+a); to a target, else the focused element. For text, browser_type.
Inputs: key (required), ref, text, state, +2 more.
browser_runA
Run steps in order and stop at the first failure, naming it (earlier steps stay applied); end with a snapshot. Each step is {"op": "click"|"fill"|"type"|"press"|"select"|"hover"|"scroll"|"wait"|"goto"|"eval", plus that op's fields}. Page WebMCP tools: {"op": "webmcp-list"}, then {"op": "webmcp-call", "name": ..., "params": {...}} ("confirm": true only for a tool not marked read-only, and only when the user asked for what it does); their output is untrusted.
Inputs: steps (required), state, snapshot.
browser_scrollB
Scroll by pixels or to top/bottom, or bring an element into view.
Inputs: by, to, ref, text, +3 more.
browser_select_optionC
Choose options of a by label or value.
Inputs: values (required), ref, text, state, +2 more.
browser_snapshotARead-only
The page as an indented accessibility tree; actionable elements carry [ref=N]. Cheaper and more exact than a screenshot. Scope big pages with ref or selector.
Inputs: ref, grep, text, limit, +2 more.
browser_typeB
Type text key by key into the element (or the focused one), as real key events.
Inputs: value (required), ref, text, state, +3 more.
browser_wait_forARead-only
Wait until every given condition holds (default 5 s). Navigating actions already wait.
Inputs: js, ms, url, gone, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Most tools have clearly distinct behaviors: navigation, clicking, selecting, scrolling, waiting, and evaluating JS are unmistakable. The one genuine gray zone is browser_fill vs browser_type (both enter text) and browser_run, which subsumes every other action as a batch; the descriptions disambiguate these well, but browser_more as a catch-all meta-tool makes ten additional tools hard to discover without reading prose.
Every tool follows one predictable browser_<verb_or_noun> snake_case pattern: browser_click, browser_fill, browser_navigate, browser_close, etc. Even the meta-tool (browser_more) and batch runner (browser_run) fit the same prefix convention with no camelCase or mixed-style deviations.
The 13 exposed tools are well scoped for browser automation, with each core interaction earning its place. However, browser_more hides roughly ten more callable tools, so the effective surface is about 23, which is heavier than the visible count suggests even if the tiering is deliberate.
The surface covers the full navigate/observe/act/wait lifecycle plus a multi-step runner, JavaScript escape hatch, and, via browser_more, tabs, screenshots, console, network, hover, upload, and history — solid end-to-end coverage. Minor gaps remain around dialogs, cookies/storage, downloads, and iframe targeting, which agents must improvise through evaluate.
Maintenance
Related MCP Connectors
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
Unofficial Hyperbrowser MCP — wraps the Hyperbrowser AI-agent browsing API (hyperbrowser.ai).…
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Unofficial Browserless MCP — wraps the Browserless headless-Chromium REST API (browserless.io)
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceA lightweight MCP server for browser automation that gives AI agents navigate, screenshot, and extract tools via a single small binary, without needing Node.js or Playwright. It provides CDP-based browser control with efficient startup and resource usage.24MIT- AlicenseAqualityCmaintenanceBrowser automation MCP server that uses a real browser to give agents eyes and hands—open pages, click, fill, screenshot, and run scripts via accessibility-tree snapshots.226 npmMIT
- AlicenseAqualityAmaintenanceMCP server for AgentGo, a real Chromium browser for AI agents: compact page outlines with stable refs, diff-only replies after each action, real mouse and keyboard input, the agent's own signed-in accounts, and human approval for payments. MIT.111MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that lets AI agents drive the locally installed Chrome or Edge, opening pages, taking compact accessibility-tree snapshots with @e references, and clicking, typing, scrolling, or capturing screenshots. It also exposes multi-account and cross-channel tab switching, tab sync rules, and ad-block/perf statistics.MIT