AI Browser
ไธญๆ่ฏป่
่ฏท็่ฟ้๏ผREADME-CN.md๏ผ3 ๅ้้่ฏป + ไธญๆๅฎ่ฃ
ๆๅผ๏ผ
A real browser whose only operator is your agent.
It reads pages as a semantic tree instead of screenshots, acts through trusted browser input โ
and because it is a normal, visible Electron window, a human can reach for the mouse at any time.
A noisy real-world feed (300+ accessibility nodes) becomes a typed structure โ then one ui.act switches the feed and the tree changes with it. Every call is a raw JSON-RPC message over one WebSocket: no SDK, no coordinates.

Reproduce: npm start then node examples/feed-tree.mjs
Human + agent, same browser, same socket. The agent drives, then simply stops and watches; a person clicks an article in the real window, the agent notices the new tab on its next read, and continues on the page the human chose. No lock, no hand-off API.

Try it yourself: npm start then node examples/human-takeover.mjs โ click anything when it says YOUR TURN.
What it is. An Electron app that exposes its tabs over two equivalent interfaces โ an MCP server
(17 browse_* tools) and a raw WebSocket JSON-RPC API (ws://localhost:9223, methods ui.*). Your
agent navigates, reads a structured semantic tree (role / label / value / states / actions),
and clicks or types by data-ai-id. Reading never goes through a screenshot and there is no OCR โ
that's the point of the tree. browse_screenshot exists, but as a diagnostic for the cases the tree
can't see (overlays, canvas, mis-rendered layout), not as the read path.
What it is not. It is not headless. The window really opens, really renders, and stays interactive โ
see Letting a human step in. Nor does it "co-drive" with you: the hand-off
is a conversation between the agent and the user, not a browser API.
Security note. The WebSocket server binds loopback only and refuses any handshake that carries
an Origin header โ that's what a browser always sends, so a page running inside AI Browser (or
any other browser) cannot drive the control plane, while Node/CLI/MCP clients (which send no
Origin) work normally. There is still no token: a local process running as you can connect.
Do not expose port 9223 beyond loopback.
(AI_BROWSER_WS_ALLOW_ORIGIN=1 disables the check โ debug only, it re-opens the page โ browser path.)
Sandbox is off by default, deliberately. Chromium's OS sandbox cannot initialise in restricted
shells (IDE terminals, some CI), where it fails with sandbox initialization failed: Operation not permitted and the app exits before any of our code runs โ so there is no error to report, just a
silent quit. AI_BROWSER_SANDBOX=1 turns it on; if the app then quits instantly with no output at
all, that's this โ unset the variable. Renderers are still isolated from the page either way
(contextIsolation:true, nodeIntegration:false); this switch is about the OS layer under them.
Install
Install the prebuilt package unless you have a reason not to. Option A is one file you
double-click: no Node.js, no dependency tree, no build step. Source install (Option C) pulls a
~276 MB node_modules plus a ~100 MB Electron engine download on top โ only use it when no
package fits your platform, the package misbehaves, or you specifically need to run from source.
Option A โ macOS install package (recommended)
Grab AI-Browser-<version>-arm64.dmg from
GitHub Releases (~110 MB to download,
~245 MB on disk โ most of it is the bundled Chromium engine, which is the product). Open the
dmg, drag AI Browser to /Applications, launch it. Done.
Two things to know before you download it:
- It is not notarized. macOS Gatekeeper will refuse to open it on the first try. Right-click
the app โ Open, confirm once, and it runs normally afterwards. (A paid Apple Developer
account is what removes this step; until then, this is the honest cost.)
- Only macOS
arm64 and Windows x64 are built. Linux has no package yet โ see
Compatibility.
Option A2 โ Windows installer
Grab AI-Browser-<version>-win32-x64-Setup.exe from the same Releases page (~79 MB). Run it and
click through: it installs per user to %LOCALAPPDATA%\Programs\AI Browser (no admin prompt,
no UAC), creates the Start Menu entry and a Desktop shortcut by itself, and offers to launch
the browser when it finishes. Uninstall is a normal entry in Settings โ Apps; it removes the
program and both shortcuts but leaves ~/.ai-browser alone, so your profiles and logins survive a
reinstall.
Two things to know:
- It is not code-signed. SmartScreen may show "Windows protected your PC" โ More info โ
Run anyway. (A code-signing certificate is what removes this step.)
- The installer is a plain NSIS wizard, so you can pick the install location; the default is the
per-user path above.
Agents still connect through the MCP server (Option B below), and the two channels cooperate:
when the packaged app is already running, the MCP server finds it on port 9223 and reuses it
instead of spawning a second copy of Electron โ one browser, one login session, whichever way
you start it. So "package for the engine + npx for the MCP bridge" is the normal agent setup
too.
Option B โ npx (the agent channel)
The package is published as @glittering0717/ai-browser;
no clone needed:
npx -y @glittering0717/ai-browser --help
To open the visible browser window directly:
npx -y @glittering0717/ai-browser start
Requires Node โฅ 18 and a desktop session (this is a GUI app). If a launch needs its own
engine, the first run prepares it (~100 MB, downloaded once). npm โฅ 11 blocks dependency install
scripts by default โ the launcher detects that and runs Electron's own downloader itself, so
nothing extra is needed. If the download from GitHub releases is slow or blocked (common on
mainland-China networks), point it at a mirror:
ELECTRON_MIRROR=https://npmmirror.com/mirrors/electron/ npx -y @glittering0717/ai-browser start
Option C โ from source (fallback)
Use this when there is no package for your platform, the package gives you trouble, or you need
to modify the code. It is the heaviest of the three: npm install pulls the full dependency
tree (~276 MB), then the Electron engine (~100 MB) on top.
git clone https://github.com/Glittering/ai-browser.git
cd ai-browser
npm install
If the Electron binary download is slow or fails outright, use the mirror:
ELECTRON_MIRROR=https://npmmirror.com/mirrors/electron/ npm install
Or make it sticky by creating a .npmrc in the project root:
electron_mirror=https://npmmirror.com/mirrors/electron/
Confirm the binary actually landed before blaming anything else โ a missing binary still leaves
you with an "install that succeeded":
ls node_modules/electron/dist
To check the install end to end:
A 1280ร800 window opens and the terminal prints AI Browser WS server listening on ws://localhost:9223.
(The first tab opens on the default start page; ignore it and navigate away.)
To build the package yourself:
npm install
node scripts/build_dmg.cjs
node scripts/build_dmg.cjs --arch arm64
Output lands in dist/. The script uses @electron/packager plus macOS's built-in hdiutil
(no external binary downloads); the reasoning โ including why electron-builder refuses to build
this project โ is documented in
docs/DEPENDENCY_AND_DISTRIBUTION_AUDIT.md.
Connect your agent
Add this to your MCP client's config file โ Claude Desktop's config, ~/.cursor/mcp.json, or a
project-level .mcp.json:
{
"mcpServers": {
"ai-browser": {
"command": "npx",
"args": ["-y", "@glittering0717/ai-browser", "mcp"]
}
}
}
A ready-made copy sits in examples/mcp-config.json. From-source users
can instead point command: "node" at /absolute/path/to/ai-browser/src/main/mcp_server.js.
You do not need to start the browser yourself. On the first browse_* call the MCP server probes
port 9223; if nothing is listening it spawns Electron detached and waits up to 30 seconds for the
WebSocket server (the very first call may additionally spend time preparing the engine). If you would
rather keep one long-lived window shared by every client, launch the AI Browser app you installed
in Option A (or run npx -y @glittering0717/ai-browser start, or npm start from source) โ a second
launch just focuses the existing window.
examples/AGENT_INSTRUCTIONS.md has a copy-paste prompt you can drop into a CLAUDE.md, Cursor Rule,
or any system prompt; it teaches the tool loop, the token-saving params, and when to ask a human.
Agents installing this themselves (Cline, etc.) can read the short machine-oriented
llms-install.md instead of this README.
Source of truth: src/main/mcp_tools.js. There are 17 โ a deliberately
small surface, since every tool schema is injected into your agent's context on every turn.
| Tool | One line |
|---|
browse_navigate | Load a URL in your tab or the given tab. |
browse_get_tree | Read the page as a semantic tree + page context (modals, messages, stats). |
browse_act | click / type (append at caret) / setContent (replace all) / clear / focus / hover / scroll_to / upload / get_value (read-only) / drag / press / wheel on a data-ai-id. |
browse_diff | snapshot a baseline, then diff to get added / removed / changed paths with before/after values. This is how you prove an action did anything. |
browse_capabilities | Probe what a page affords and which route to take on it (see below). |
browse_repaint | Force the compositor to redraw the tab when the window shows a stale page; returns repaint_count. |
browse_downloads | List a tab's downloads with their on-disk paths. Downloads are asynchronous โ poll this after clicking an export button. |
browse_canvas | Read <canvas> through captured draw calls: list / read / configure / capture. Experimental โ see the canvas section below. |
browse_evaluate | Run a JS expression in page context (5000-char cap, Node identifiers rejected). |
browse_scroll | Scroll the page, or scroll an element into view. |
browse_wait | Poll until button_enabled / modal_appeared / text_contains / url_contains. |
browse_tabs | Tabs: list / new / close / switch / window. switch = default; add show:true. new never steals the view unless show:true. |
browse_network | Chrome-DevTools-style network inspection: list (filter by method / URL / status / type), get (request + response headers and bodies), clear, configure. |
browse_auth_state | Login-state self-check for a tab: are we logged in, or bounced to a login wall. Cheap โ no tree is built. |
browse_screenshot | Diagnostic viewport/element capture (png/jpeg/webp, clip, fullPage, source: auto/surface/cdp). Not the read path โ use it when the tree and the screen disagree. The receipt says which tier answered. |
browse_errors | Recent errors the browser recorded (crashes, failed navigations, RPC failures) with hints. Ask here when behaviour doesn't match the docs. |
browse_quit | Shut the whole browser down and release the process. |
What every act result already tells you: effect_state
browse_act no longer leaves you guessing whether your input reached the page. Every result
carries an explicit verdict:
effect_state | Meaning | retry |
|---|
committed | dispatched and acked by the page | no |
none | provably nothing happened (no such target, bad params, CDP down) | safe |
unknown | cannot prove nothing happened โ timeout, paste dispatched but never consumed, half a key sequence | verify_first |
The default is unknown, not none: when the browser cannot tell, it says so. Retrying an
unknown blindly is how a form gets submitted twice โ read the page first. unknown results
also carry a one-sentence effect_hint saying exactly that.
When a target cannot be found, the result adds stale_ref / ref_epoch / tree_epoch /
ref_diagnosis, because "no such target" hides three very different situations:
ref_diagnosis: "stale" โ the page was re-read after you took that ref (ref_epoch <
tree_epoch). Get a fresh one; retrying the same ref will keep failing.
ref_diagnosis: "never_seen" โ the ref has never been in any tree read so far. Re-reading
will not help: wrong value (visible text instead of a data-ai-id), a typo, or another tab's ref.
ref_diagnosis: "present_in_tree" โ in the current tree but not found in the DOM: iframe,
shadow root, or a detached node.
All three report effect_state: "none" (nothing happened) with retry: "verify_first" โ no side
effects, but repeating the identical call is pointless.
Prove it happened: browse_diff
A tool reporting success is not evidence that anything changed โ the browser will happily
tell you a click landed on an element that ignored it, a drag completed when the app snapped the
node somewhere else entirely, or a keystroke went into a field that then cleared itself. Every
write should be wrapped in a snapshot/diff pair:
const base = await browse_diff({ operation: "snapshot", js: "app.graph.serialize()" });
await browse_act({ action: "click", target: "e:button-25" });
const d = await browse_diff({ operation: "diff", snapshot: base.snapshot });
verdict is an explicit "changed" / "unchanged", so "nothing happened" is never inferred from
an empty array you might have built wrong.
- Every entry carries a
path plus both values, so you can check why it changed.
- Arrays are compared element-wise by index, not as sets: a moved node reads as changed entries,
never as "one removed + one added" (which would look like two events instead of one reorder).
- Float noise is tolerated (
201354.48743718592 vs ...1859 is not a change), but a real 22-unit
coordinate shift is.
- Omit
js for a site-agnostic DOM snapshot โ role / label / value / disabled / size per
element plus the page's visible text. No per-site JS required, and plain <div> status text
changes are caught.
- Omit
js and it also fingerprints the app's own data model when the page hangs one off
window. A canvas-rendered app's DOM is a still photograph โ dragging a node or editing a
widget repaints <canvas> and moves nothing the element walk can see, so a DOM-only diff
answers unchanged to a write that demonstrably happened. ComfyUI's documented write path
(node.widgets[].value) moved the DOM by exactly zero bytes. With the fingerprint, that same
write shows up as model.fp (and model.count when the node count moved). It is read-only
(loadGraphData is a loader and is never called), it picks whichever candidate can actually be
read back rather than whichever looks most promising, and a library namespace โ which scores
well on names and has no model to hand back โ is skipped.
rearm: true moves the baseline forward for the next diff, so you can loop "assert nothing
changed" across many steps; forget: true drops it.
- A throwing expression, a missing id, or a cross-tab comparison all return an explicit error.
They never degrade into an empty snapshot, which would make every subsequent diff report
"unchanged" โ the one failure mode that turns all verification into false green.
Which route on this page? browse_capabilities
Before improvising on an unfamiliar site, ask. One call reports the semantic-tree size and its
role/action histogram, canvas count, same-origin iframes and their internal size, objects the app
hangs off window (auto-detected by shape: has .graph / ._nodes / getState / serialize),
the JSON endpoints it has already called, and a recommended route with the evidence for it:
L1_structured_data โ the app exposes its own model; read and write the whole graph as JSON.
L2_semantic_tree โ enough elements to find targets by role/label and drive them by data-ai-id.
L3_pointer_gestures โ only for what has no structured path (drag a node, draw a connection,
wheel pan/zoom). Always follow with browse_diff.
It also flags traps explicitly: "the body is in a same-origin iframe" or "there are 7 canvases but
only 17 semantic elements โ stop trying to hit canvas-drawn items with coordinates and go find the
data model instead".
Notes that save round-trips:
browse_get_tree accepts subset: "interactive" to drop layout-only branches, mode: "diff" to
return only nodes that appeared/disappeared since the last read, and ax: true to read through the
accessibility layer (links then carry url).
type appends; setContent replaces. They used to be identical (both replaced the whole
content), which made incremental editing impossible โ insert a Weibo-style topic tag and the next
type wiped it. Now type writes at the caret (params.at: end (default) / start /
cursor), so "insert a topic, then keep writing the body" works. To refill a field, use
setContent (or clear first).
browse_act also takes action: "get_value" โ a read-only way to fetch an element's full text,
which matters because browse_get_tree truncates long values at 200 characters (see below).
- Pointer gestures are first-class:
drag, press and wheel. Canvas / board / sortable UIs are
built on them, and no amount of evaluate can substitute โ synthetic PointerEvents do not move a
framework that uses Pointer Capture (measured on a React Flow canvas: the node's position changed by
exactly 0,0), so these go through CDP trusted input.
drag: dx/dy, to_x/to_y, or to_target (drop onto another element). from_anchor
/ to_anchor (left/right/top/bottom/center) grab a side โ a side prefers that element's
connection handle, but only if the handle is actually hit-testable (see the note below).
from_x/from_y start from a bare point (panning empty canvas), in which case no target is needed.
press: key (Delete, Escape, ArrowRight, Enter, โฆ or a combo like "Meta+a"), or keys
for a sequence. Deleting a node, undo, deselection โ all keyboard-only.
wheel: delta_x / delta_y plus hold: ["Control"] for canvas zoom. browse_scroll cannot do
this โ it calls window.scrollBy, which an infinite canvas ignores entirely.
- The drag result reports
drag_from / drag_to and which element actually sits at each point
(from_at_id), plus warning + start_hit_target: false when the press landed on a different
element โ visual overlap otherwise looks exactly like "drag does nothing".
actions is inferred from behaviour, not from role. An element whose computed cursor is a
drag cursor, or that has draggable="true" / cursor: pointer / an onclick, now advertises
drag / click in the tree even when its role is group. Without this, a canvas full of
role: group nodes reported actions: [] and the agent could not tell they were interactive at all.
browse_network captures requests from the moment a tab opens, including POST request bodies โ
no subscription needed. Request headers are redacted by default
(authorization / cookie โ [REDACTED]); pass include_sensitive_headers: true to see them.
- Most tools take an optional
tab for multi-tab work; omit tab to target your own session tab.
Letting a human step in
It does not steal your focus โ and it does not need a window at all
The agent works fine while the window is in the background, minimised, or not shown at all.
CDP trusted input (Input.dispatchKeyEvent / Input.dispatchMouseEvent) does not need the window to
be frontmost, and the app runs with disable-backgrounding-occluded-windows,
disable-renderer-backgrounding and disable-background-timer-throttling, so a hidden window is
neither throttled nor losing events. Every tab also gets setBackgroundThrottling(false) from birth.
Three things used to make "run it in the background" impossible, and all three are fixed:
new_tab / set_active_tab dragged the window to the front on every call (they called
webContents.focus()). They no longer do. The page still thinks it is focused โ
Emulation.setFocusEmulationEnabled keeps document.hasFocus() and focus-dependent lazy-loading
behaving normally โ while your keyboard focus stays wherever you left it.
- Any action un-hid a hidden window (
auto restored it with showInactive()), so "hidden" was
never a steady state: the window crept back up every time the agent clicked something. Visibility is
now driven only by you (Dock icon) or by an explicit ui.window call.
- A tab that was never attached to the window had no compositor surface: reading, clicking and
typing worked, but
screenshot returned 0 bytes and paint_check reported no-frame โ a black box.
All tabs are now attached and z-ordered (setTopBrowserView), so a background tab renders and can be
screenshotted.
AI_BROWSER_START_HIDDEN=1 npm start
AI_BROWSER_FOCUS=always npm start
AI_BROWSER_FOCUS=never npm start
AI_BROWSER_INPUT_FOCUS=0 npm start
While it is hidden, everything still works โ read the tree, click, type, scroll, upload, download,
answer dialogs, capture network, screenshot, paint_check. Click the Dock icon at any moment and the
window appears showing the tab you were looking at; the agents keep working on theirs.
โ ๏ธ "click and type work while hidden" is a promise the browser now makes true, not a property of
Chromium: simulated input is dropped on any document reporting visibilityState: hidden, so each
trusted-input action first checks that tab and, if needed, gives it the page-focus emulation the front
tab already has (see Tab groups above). AI_BROWSER_FOCUS=never switches that emulation off
altogether, and then a hidden window genuinely cannot receive simulated input โ ui.act fails with
input_blocked: true instead of reporting success. That is the honest outcome, not a regression.
npm run focus asserts the focus behaviour from the outside (macOS lsappinfo, no accessibility
permission needed) with a deliberate control group configured to steal focus, so the suite goes red if
the measurement ever stops working instead of passing vacuously. npm run background covers the
window-hidden half: it boots with AI_BROWSER_START_HIDDEN=1 and runs the full capability slice
against a window that never appeared.
Note on document.hasFocus(): it returns true even when the window is in the background, because
Emulation.setFocusEmulationEnabled is deliberately on โ that is what keeps focus-dependent
lazy-loading and animations from stalling. So it is not a valid way to detect "am I in the
foreground"; the test uses the external observer instead.
Several agents at once
Each WebSocket connection (each MCP process) gets its own working tab. When a call omits tab,
the target is resolved as explicit > your tab > the tab the human is looking at > the first tab, so:
browse_tabs {"op":"new"} opens a tab without taking over the user's view (show:true when you
want them to look at it). The single exception is the untouched start page โ otherwise the user
would sit staring at a blank homepage while the agent works.
browse_tabs {"op":"list"} marks your own tab with mine: true.
- If someone else closes your tab, your next call fails with
-32001 instead of silently running
on their page. Closing your own tab falls back to the visible one, like a normal browser.
- Tabs opened by a click (
target=_blank) move your target to the new tab; they only move the
user's view if the tab they were watching is the one that opened them.
Different tabs run fully in parallel. Two agents typing into the same field is not coordinated โ
the write-verification will honestly report input not verified rather than pretending both landed.
npm run multiagent drives two connections against one browser and asserts all of the above,
including 10 interleaved actions with no cross-contamination.
Tab groups: every agent gets its own corner
Targets are per-connection, but tabs still shared one strip โ you could not tell whose tab was whose,
and nothing stopped an agent from opening twenty of them. Both are fixed by ownership:
group = 'human' | 'agent:<session>'
An agent declares itself with ui.hello (the MCP server and the CLI both do it on connect). From then
on, the first call that touches a page and has no target yet gets a blank tab of its own, in its own
group, and a one-time hint in the result:
{"workspace": {"tab": 7, "group": "Claude", "created": true, "hint": "..."}}
So an agent never defaults to the tab you are looking at. Reading your page is still possible and
still cheap โ browse_tabs {"op":"list"}, find the entry with group: "human", pass its tab
explicitly. Reading does not take it over.
In the tab strip your tabs stay as they were; each agent group collapses into a pill (its colour, name
and tab count), expands on hover, pins on click, and stays expanded while you are looking at one of its
tabs. Clicking a tab inside a group only changes what you see โ it does not change the agent's target.
Each group is capped (8 by default, AI_BROWSER_TAB_LIMIT). Opening past the cap is refused, not
"quietly evicted", with the list of tabs you could close:
-32001 your tab group is full (8/8) โ close one before opening another
data: { reason: "group-full", limit: 8, tabs: [{tab, url, draft?, downloading?}, ...] }
Over MCP the agent receives this as a tool result with isError: true and the readable text
Error: your tab group is full (8/8) โ close one before opening another โ a normal tool failure it
acts on, not a JSON-RPC protocol error. The data fields above are the raw-WS detail.
Popups cannot be refused (the page's script is waiting for the window), so in that one case the least
recently used tab in the group is closed instead โ never the visible one, never one with a dialog
open, and since 2026-11-03 also never one holding unsubmitted input (a type/setContent/paste
that hasn't been followed by a real navigation) or an in-progress download. The reason for the
last two is that eviction here is a full tab close, harsher than Chrome's discard: a discard leaves
the form, our close leaves nothing. If nothing qualifies, the group is allowed one tab over the cap โ
better a page too many than a page you were working on swallowed. Whatever got closed is reported in
browse_tabs {"op":"list"} as evicted, and the two protections are marked in the refusal payload
(tabs[].draft / tabs[].downloading) because when it's your turn to decide what to close, that's
the only evidence you have.
Sound follows the visible tab only. Every tab lives in one window and z-order decides which one
the human sees โ audio has no z-order, so an agent's background video plays out loud and there is no
speaker to find. Non-active tabs of an agent group are muted from birth; the tab in front and your own
tabs are never muted (Chrome leaves those playing too). Muted tabs carry muted: true in
browse_tabs {"op":"list"}. Muting is output gain, not pause: currentTime keeps advancing, so
the page the agent reads is not secretly a stalled one. Turn the rule off with AI_BROWSER_BG_MUTE=0.
Trusted input reaches the tab you aimed at, not just the visible one. Chromium drops simulated
input on any document that reports visibilityState: hidden โ and in a window that was never shown,
the only page that reports visible is the one that got CDP page-focus emulation, which the browser
normally hands to the front tab alone. The old shape was the worst possible one: the event vanished,
nothing was clicked, and ui.act still answered {success:true, clicked_via:'cdp-click'}. So before
every trusted-input action (click/hover/drag/wheel/type/setContent/clear/press/paste)
the browser asks that tab "are you visible?", and if it isn't, hands it the same focus emulation it
already gives the front tab โ no z-order change, no window shown, activeTab and mute state untouched,
and nothing is restored afterwards (the emulation is sticky; toggling it would put every page through
visibleโhiddenโvisible on every action). If a tab still can't receive input, the action is not
dispatched and the receipt says so: success:false + input_blocked:true + the page's visibility,
with the escape hatches named (JS path via ui.evaluate, or show the window once). Measured 2026-11-03:
raising the tab (setTopBrowserView), webContents.focus(), detach+reattach, setBounds,
setBackgroundThrottling(false) and Page.setWebLifecycleState{active} do not deliver input;
Emulation.setPageVisibilityOverride does not exist in Chromium 130. "The active tab is always visible"
turned out to be false too โ under AI_BROWSER_FOCUS=never even it reports hidden and input is dropped,
which is why every trusted-input action pays one short (800ms-capped) probe. AI_BROWSER_INPUT_FOCUS=0
turns off the emulation only; honesty about the failure is not switchable.
npm run multiagent (80 checks) covers the positive half โ M11 clicks and types into a background tab
in a never-shown window while the control tab and activeTab stay put. npm run input_routing
(15 checks, two instances) covers the honest-failure half under AI_BROWSER_INPUT_FOCUS=0 and
AI_BROWSER_FOCUS=never. Both also pin the rest of it: auto workspace, the cap and its refusal payload,
that one full group does not affect anybody else's, who gets evicted when a popup needs the space, and
that a muted tab is still playing.
This is the part most easily misunderstood, so plainly: the agent drives the browser, and the human
can always take over the window.
Because it is a real Electron window, a person can click, type, scroll, and log in exactly as they
would in Chrome โ with the mouse and keyboard, at any moment, with no permission to request. That
covers the things an agent genuinely cannot do:
- Login / SSO and anything behind a password the agent shouldn't have
- QR-code scans (app-to-web authorization)
- Slider and image CAPTCHAs, SMS or email codes
- Payment confirmation, risk-control interstitials, OTP screens
- Anything where continuing would mean fabricating credentials
How the hand-off works: there isn't one โ in the browser. Nothing coordinates it on AI Browser's
side, and nothing needs to. It is a conversation between the agent and its user:
- The agent hits something it cannot do.
- It says so in its own reply, as plain text โ "Please scan the QR code in the browser window, then
reply 'done'." No tool call is involved: there is no
chat / message / ask_user tool in this
project, and no "spawn a side conversation" feature. Talking to the user is the agent's own job.
- It stops and waits for the reply โ no retry loops on clicks that cannot work.
- After "done" it re-reads with
browse_get_tree to confirm the new state, then continues.
See examples/with-human.mjs for the scripted equivalent: it prints a
prompt and waits for Enter over readline. The browser has no idea any of that happened.
Two practical consequences for the agent:
- Never call
browse_quit while a human is working in the window. It tears down the window and
exits the process โ anything half-solved is lost. Quit when the task is finished, not before.
- Login state persists. Tabs live in the
persist:ai-browser session partition, so cookies and
sessions survive a restart; usually a human only has to step in once per site per machine.
Raw WebSocket API
MCP is a thin stdio adapter. Anything MCP can do is reachable directly over JSON-RPC 2.0 at
ws://localhost:9223 from any language. Source of truth: the method switch in
src/main/ws_server.js.
Two things to know before you write a client:
- Connections carrying an
Origin header are closed with code 1008. Browsers always send it;
Node's WebSocket and the ws package do not, so a normal script is unaffected. This is a
security boundary, not a bug โ see the security note above.
- Method parameters are camelCase (
focusedOnly, timeout_ms). MCP maps the snake_case tool
arguments onto them.
You do not have to write a client to do this. The CLI speaks the same protocol:
ai-browser status
ai-browser call ui.list_tabs
ai-browser call ui.get_tree '{"subset":"interactive"}'
ai-browser call ui.navigate '{"url":"https://example.com"}'
echo '{"url":"https://example.com"}' | ai-browser call ui.navigate -
call prints the raw result as one line of JSON (pipe it into jq), exits 0 on success,
1 when the call failed, 2 on a bad command line. --port, --timeout, --pretty are available.
So there are three doors to one implementation โ MCP stdio (ai-browser mcp), JSON-RPC over
WebSocket, and this CLI. None of them is a separate code path.
| Method | Purpose | Maps to |
|---|
ui.get_tree | Semantic tree (+ context). Params: focusedOnly, ax, subset, mode, tab | browse_get_tree |
ui.act | params.action + params.target; per-action args nested under params.params | browse_act |
ui.navigate | Load a URL (params.url, optional tab). Returns {ok, error?} โ {ok:false} always carries a reason. | browse_navigate |
ui.snapshot / ui.diff | Capture a baseline (params.js, optional label) and diff against it (params.snapshot, rearm, forget) | browse_diff |
ui.capabilities | Probe the page: tree histogram, canvas, iframes, app globals, endpoints, recommended route | browse_capabilities |
ui.repaint | Force the compositor to redraw a tab; returns repaint_count so a repaint is provable | browse_repaint |
ui.evaluate | Run JS in page context, same guard as MCP | browse_evaluate |
ui.scroll | Scroll page or element (direction, amount, target). Document scrolling only โ for canvas apps use ui.act{action:'wheel'}. | browse_scroll |
ui.wait | Poll until a condition or timeout | browse_wait |
ui.new_tab / ui.close_tab / ui.list_tabs / ui.set_active_tab | Tab management (the four are merged into browse_tabs{op} on the MCP side) | browse_tabs |
ui.subscribe / ui.unsubscribe | Event subscription; params.events, "*" for all | โ (WS only โ see below) |
ui.downloads | This tab's downloads with on-disk paths (state, received_bytes, dir) | browse_downloads |
ui.get_focused | The focused element subtree | โ |
ui.peek | Hover a folded/hover-only affordance and return what appeared/disappeared (revealed / hidden), without committing. Ids are real data-ai-ids you can hand straight to ui.act; revertMs: 0 keeps the mouse there so you can click what it found | โ |
ui.network_body | Response body by URL substring (url_pattern) | โ (superseded by browse_network) |
ui.quit | Graceful shutdown | browse_quit |
Note two differences from the MCP spelling, both visible in the switch above: it is focusedOnly
(camelCase), not focused_only; and ui.act nests its per-action arguments under params.params.
ui.subscribe / ui.unsubscribe are also valid as notifications with no id.
ui.subscribe is deliberately not exposed as an MCP tool: MCP's stdio path drops
serverโclient notifications, so an MCP caller would subscribe and then never receive a single
event. Real-time events are a raw-WebSocket capability only. For anything pull-based, use
browse_network instead.
import WebSocket from 'ws';
const ws = new WebSocket('ws://localhost:9223');
let id = 0;
const call = (method, params) => new Promise((resolve, reject) => {
const myId = ++id;
const onMsg = (raw) => {
const m = JSON.parse(raw.toString());
if (m.id === myId) { ws.off('message', onMsg); m.error ? reject(new Error(m.error.message)) : resolve(m.result); }
};
ws.on('message', onMsg);
ws.send(JSON.stringify({ jsonrpc: '2.0', id: myId, method, params }));
});
ws.on('open', async () => {
await call('ui.navigate', { url: 'https://example.com' });
const { tree } = await call('ui.get_tree', { subset: 'interactive' });
console.log(tree.role, tree.children?.length);
ws.close();
});
Error codes follow JSON-RPC: -32700 parse error, -32601 unknown method, -32602 invalid params
(the ui.evaluate guard returns this), -32603 internal error.
How it works
agent โโ MCP stdio (17 browse_*) โโโ
agent โโ WS JSON-RPC :9223 (ui.*) โโค
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Electron main โ
โ index.js window ยท tab strip ยท watchdog โ
โ ws_server.js JSON-RPC routing, event stream โ
โ page_manager.js tabs ยท id-matched IPC ยท CDP โ
โโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ IPC (request-id matched)
โโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ preload (contextIsolation:true, nodeIntegration:false)
โ bridge.cjs ยท extractor.cjs ยท actions.cjs ยท โ
โ watcher.cjs (captcha / message / state scan) โ
โโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โผ
live DOM โ semantic tree
Reading. Each node in the returned tree carries a data-ai-id โ the element's own DOM id when it
has one, otherwise a generated e:tag-N. Ids are stable across reads: an element that already
carries one keeps it, and generated ids come from a monotonic counter, so inserting an element above
others does not renumber them. (It used to: a stale id then silently resolved to a different element,
and the act reported success while hitting the wrong thing.) They reset on navigation. Alongside the id
come role, label, value, states, and actions, plus a context block โ open modals, transient
messages, required-field hints, coarse stats. Two read paths exist: the default preload extractor, and
the accessibility layer behind ax: true (which additionally gives links their url).
The first read of a page annotates elements with data-ai-id; that is the one write a read performs,
and it is what makes later acts resolvable. Repeat reads write nothing. An attribute is only set
when its value actually changes, because real Chromium delivers a MutationObserver record even when
you set an attribute to the value it already holds โ measured at 4001 records per read on a
4000-element page before this guard existed. A read that spams the page's own observers is a read that
perturbs the thing it is measuring.
Writing. Actions are trusted browser input, not synthesized JS. The main process drives the
page over the Chrome DevTools Protocol โ Input.dispatchMouseEvent for clicks, and per-character
Input.dispatchKeyEvent (rawKeyDown โ char โ keyUp) for typing โ then validates that the click
actually landed via elementFromPoint (piercing shadow roots: the plain call returns the host for
anything inside a web component, which silently downgraded every such click to a synthetic one).
Because the events arrive as real keyboard and mouse input,
Draft.js, ProseMirror, CKEditor, Quill, and plain <textarea> all work through the same path without
per-framework branches.
Popups. A site asking for an overlay โ window.open(url, name, 'width=420,height=520,left=120,top=80')
(login boxes, payment QR codes, pickers) โ gets one: that tab's view is placed at exactly the rectangle it
requested, on top of its parent, instead of filling the window. The geometry is read from the third argument,
which this project used to discard on both entry points (the handler destructured url, the page-world shim
named its parameter _features and never used it), so every 420ร520 login box grew into a full-size tab and
laid itself out for 1280px. Only size-bearing features count, exactly as in Chrome: noopener / _blank are
not sizes and still open an ordinary tab โ the suite runs that negative control in the same pass. Shrinking
the window re-clamps the overlay; growing it does not enlarge the overlay back. ui.list_tabs adds a popup
rectangle for those tabs, because clicking or screenshotting them on full-window coordinates misses.
Where it is thin. extractor.cjs is a heuristic over the DOM, not a clean-room specification: it
handles ordinary pages well and will mislabel exotic ones. The window runs with hardware acceleration
off plus three Chromium switches
(--disable-backgrounding-occluded-windows, --disable-renderer-backgrounding,
--disable-background-timer-throttling) so that an IDE window on top of the browser doesn't cause
injected input to be silently dropped.
Examples
Runnable scripts live in examples/ and connect straight to ws://localhost:9223:
node examples/read-page.mjs
Troubleshooting
The page updated but the window still shows the old one. A BrowserView's surface is only
re-rasterized when something forces it, so the app asks for a repaint on window show / restore /
focus โ that matters because this window is designed never to steal your focus, so it can sit behind
your editor for minutes while the agent works. ui.repaint forces it on demand and reports
repaint_count, the only externally observable proof that a repaint actually happened.
Two things to know about that knob:
- The default is soft (
webContents.invalidate()): it never touches geometry, so it cannot make
the window jump. It is deliberately not stronger. A 1px bounds nudge is the only thing that rebuilds
a surface whose pixels are wrong, and it costs two relayouts โ which is exactly the
"grows-then-shrinks, flickers" complaint this app got when that ran on the hot paths
(e2e/layout_ws G4/G5 now pin navigation and tab-switch to zero repaints by default).
- "A login overlay with a different site behind it" is not this class of bug (root-caused
2026-11-02). Every tab's view stays attached to the window, stacked on the same bounds, and
only z-order decides which one you see โ but z-order decides who is on top, not that the top
one is opaque. A page with a transparent root background (a login page designed to live inside
an iframe overlay, opened as a top-level document; its own captured frame measured 86.3% of
pixels with alpha<255) reveals whichever tab sits directly underneath it. Each tab view is now
created as an opaque surface (
#FFFFFF, the same thing a real browser does with a
transparent top-level page), so those pixels are filled by that tab itself. npm run paint P6
pins the invariant: an active tab's frame must not contain a single transparent pixel.
- If you really are seeing this tab's own stale pixels โ the DOM reports the new page while
the window shows the old one โ set
AI_BROWSER_HOT_REPAINT=hard and take the flicker: it
upgrades repaint on navigation-finish, tab switch and window re-show. disable-back-forward-cache
is not the lever here; bfcache stores the page you navigate away from, so it cannot explain a
stale frame on a forward navigation, and switching it off costs you the instant back/forward restore.
Separate bug, same "the screen is lying" family: during the few hundred milliseconds between pressing
Enter and the new document committing, webContents.getURL() still returns the old page, so the
address bar used to flash back to it. It now shows the requested URL while state is loading
(list_tabs reports it as pending_url, never as url โ an agent that read the target in url
would assume it had arrived and scrape the previous page).
An action reported success but nothing changed. Two causes worth knowing:
- Over raw WS,
ui.act nests its per-action arguments under params.params โ {action:"type", target:"<id>", params:{text:"โฆ"}}. Flattening it to {text:"โฆ"} passes an empty string, which
used to hit the idempotent short-circuit and report success with nothing typed. It now returns
an explicit error instead.
- Sometimes the action genuinely did nothing (an overlay ate the click, the app reverted the
change). That is what
browse_diff is for โ wrap the write in a snapshot/diff pair rather than
trusting the return value.
An action never returns at all. Every path that goes into the page is bounded by a deadline, so a
page whose main thread is blocked (a heavy recompute, a huge JSON.parse, a third-party script in a
loop) can never hang your tool call. Measured against a page that occupies its main thread for 120s:
| Call | Behaviour |
|---|
ui.get_tree / ui.get_focused | errors at 5s (getTree timeout) |
ui.evaluate | errors at 10s (CDP 5s, then the preload fallback's 5s) |
ui.act | returns at 15s with success:false, timed_out:true |
ui.capabilities | returns normally (~15s) |
ui.list_tabs / ui.network_list | instant โ they never touch the page |
ui.act's budget scales with the work requested, so a legitimate long operation is not killed: type
/setContent budget text.length ร interval_ms, drag budgets duration_ms + steps, press
budgets repeat ร interval_ms, clear gets 20s. Override with params.params.timeout_ms
(1s floor, 300s cap) or globally with AI_BROWSER_ACTION_TIMEOUT_MS. A timeout explicitly warns that
the action may have partially applied โ pointer already down, half the characters typed โ so
re-read before retrying rather than firing the same write twice.
The app restarts itself. Electron's NetworkService can wedge as a whole: the port still listens,
every navigation fails with ERR_FAILED, and curl works fine. A watchdog probes from the main
process every 30s; after 5 consecutive failed sweeps it broadcasts network_wedged and relaunches
(the MCP client reconnects on its own). With a 5s per-request deadline that puts a genuine wedge at
roughly two minutes.
- Change what it probes:
AI_BROWSER_WATCHDOG_URLS=https://www.baidu.com/,https://example.com/
(comma-separated). The default is example.com plus www.baidu.com, and that plurality is
deliberate โ the network counts as alive if any target answers, so one flaky or geo-blocked host
can't trigger a reboot loop. Never set a single target that your network can't reach.
- Turn it off entirely:
AI_BROWSER_WATCHDOG=0 (also accepts off / false / no).
Port 9223 is already busy. Another instance โ often a stale one from an earlier session โ owns the
port, or something else does. Either quit that instance, or move AI Browser off it:
AI_BROWSER_PORT=9224 npm start
Keep the port consistent across every client; both the app and the MCP server read
AI_BROWSER_PORT from src/shared/config.js.
Electron is missing or launch fails immediately. The ~100 MB engine never landed. With the npm
package, just launch again โ the launcher downloads it itself (set ELECTRON_MIRROR for a slow
network, see Install). From source, check ls node_modules/electron/dist and re-run
npm install with the mirror. Setting AI_BROWSER_PORT will not help here โ this is a missing
binary, not a port conflict.
Input is accepted but nothing happens. Usually the window is occluded. The three
disable-*-backgrounding switches above exist to prevent it, but if you still see clicks that report
success while nothing moves, bring the AI Browser window to the front and try again.
Login state keeps getting lost. Sessions persist under ~/.ai-browser. If you override it, note
that separate AI_BROWSER_USER_DATA directories are separate session stores โ "logged in" in one is
not "logged in" in another:
AI_BROWSER_USER_DATA=~/.ai-browser-work npm start
A red bar appeared at the bottom of the window. That is a main-process exception โ a bug in
AI Browser itself, not in the page you were driving. It is deliberately not a modal dialog: a
native dialog.showMessageBox is an NSAlert modal loop on macOS and blocks the whole main process
(measured: WebSocket calls got 4ms with no dialog vs 8 seconds of no response with one), which
turned a self-healing JS exception into "every RPC timed out". The bar shows the message and the log
path, the process keeps running, and you can dismiss it with ร.
Every exception is appended synchronously to ~/.ai-browser/logs/error.jsonl (2MB ร 4 rolling), with
the last 20 WebSocket calls attached so you can see what was being done when it broke. Read it over
the API with ui.errors / browse_errors, or just tail the file. A record of boot without a
matching shutdown means the process died hard last time.
If the exception happened before any window existed, the bar has nowhere to go, so it falls back to a
native box once (logged as error_dialog_fallback) rather than leaving you with a silently dead app.
Both paths are switchable: AI_BROWSER_ERROR_BANNER=0 disables the bar, AI_BROWSER_ERROR_DIALOG=1
forces the modal box โ the latter blocks the main process, so it is only for staring at a startup
crash on purpose.
A site calls it a captcha or "this browser may not be secure"
Risk control does not detect "automation" as a concept; it looks for a browser whose own fields
disagree. Ours did (measured 2026-11-01 against the same machine's Chrome 156): the UA said
Macintosh โฆ Chrome/130, navigator.platform said Win32, sec-ch-ua-platform said "Windows",
and WebGL reported a Windows D3D11 adapter. That combination does not read as "a Mac browser", it
reads as "someone edited this browser" โ hence Baidu's slide captcha on almost every search and
Google's interstitial. So identity is computed by one function from the real runtime
(src/shared/browser_identity.cjs) and delivered in three layers: UA + UA-CH metadata through CDP,
Accept-Language as a clean preferred list (no ;q=0.9 โ that value also lands in
navigator.languages), and the navigation-time sec-ch-ua* headers, which Electron's engine does
not emit at all on document requests (page-initiated fetch does), added at the request egress.
Ask the app instead of guessing:
node bin/ai-browser.cjs call ui.server_info
Google sign-in has a second, separate trap (six-arm measurement, 2026-11-05). Our UA used to be
a pure Chrome/130.0.0.0 string with Google Chrome in the brand list โ i.e. we claimed to be
official Chrome. Google then holds you to Chrome's browser-layer attestation (window.chrome's Gaia
bindings plus the install state), which an Electron shell cannot produce, and the sign-in page
answers /v3/signin/rejected?rrk=46. The closer you impersonate, the harder the verdict. The UA now
carries our own product token (ai-browser/2.5.2 โ Edge sends Edg/, Vivaldi sends Vivaldi/, for
exactly this reason) and the brand list reports Chromium only. We are Chromium; that is true. Same
machine, same account, same email-only submission: the server now continues to the password step.
AI_BROWSER_BRANDS=chrome and AI_BROWSER_IDENTITY=0 exist only to re-run either arm of that
comparison โ do not ship them. Details and the full table: docs/SPEC.md, "Google ็ปๅฝ".
What is still genuinely different, and what to do about it:
- The engine is 26 majors behind (
Chrome/130 vs a current Chrome/156). Consistent, but an
"outdated browser" signal on its own. The only cure is upgrading Electron โ a dependency bump, so
it is a deliberate release, not a patch.
window.chrome.loadTimes / .csi are absent (old Chrome telemetry stubs). Low weight, not
yet filled.
data-ai-id is written into the live DOM while reading the tree (70 attributes on Baidu's
homepage). It is load-bearing for the CDP selector path, so removing it is a refactor, not a
switch โ site scripts can see it. This is the loudest tell left.
- The canvas recorder and the
window.open shim patch page-visible natives. Both are now
opt-in (AI_BROWSER_CANVAS_HOOK, AI_BROWSER_POPUP_SHIM), and the __ai_browser__ bridge is no
longer exposed to site pages at all โ see the canvas section above.
The element is clearly on the page but not in the tree
Before you write a site-specific script, work down this list. The reflex โ "pin it with a
querySelector chain" โ is what produced 142 site-specific scripts and 731 hardcoded selectors in
this project's own history, and almost none of them turned out to be necessary.
| # | Check | How | If it is the cause |
|---|
| 1 | Is it a read-layer gap? | node tools/coverage_probe.cjs https://the.site/ | the tree is missing clickable elements โ report it; the fix belongs in src/preload/extractor.cjs, not in your script |
| 2 | Is it an action-layer gap? | the node is in the tree, ui.act fails or does nothing | the element is readable but not reachable (iframe/OOPIF, canvas, trusted input, un-mounted input) โ that is a browser-side fix too |
| 3 | Is it timing? | re-read the tree 2โ3s later, or wait_until | the SPA simply had not rendered when you read it |
| 4 | Does it only exist while hovered? | ui.peek { target, revertMs: 0 } | the affordance is hover-rendered. peek hovers it and returns what appeared โ pass revertMs: 0 to keep it open, then ui.act click the id you got back |
| 5 | Is it unnamed? | ui.peek, or click it and read what shows up | an icon-only button the site gave no aria-label/title/alt cannot be named from nothing. But the panel it opens usually is named โ so open it and read that instead of guessing which icon is which |
| 6 | Only now: pin it yourself | a selector in your script | keep it in your script. Do not encode it as "how this site works" โ the next site will not match |
coverage_probe counts what a human would call click targets โ elements the browser itself renders
with a hand cursor (cursor:pointer), where the pointer starts (not every descendant that inherits
it), and reports how many of them carry a data-ai-id:
$ node tools/coverage_probe.cjs https://www.csdn.net/
ๅฏ็น็ฎๆ ๏ผๆๅ่พน็๏ผ: 257
โ ่ชๅทฑๅธฆ data-ai-id๏ผ็ดๆฅๅฏๆไฝ๏ผ: 257 โ 100%
โ ่ขซๅไธชไบคไบๅไปฃ็ๆปกไธๅฎๅจๆ ้๏ผๅฃณๅญ๏ผ็นๅ
ๅฑ็ญไปท๏ผ: 0
โ ็ฅๅ
ๆญงไน๏ผๅไธ็ฅๅ
ไธๅคไธชๆๅๅไปฃ๏ผ็น็ฅๅ
ๆไธๅ๏ผ: 0
โ ๆดๆก็ฅๅ
้พๆ id๏ผ็็ไธ่ง๏ผ: 0
ๅฏ็จ็๏ผin_tree + by_desc + anc_only๏ผ: 100 % | ็็ผบๅฃ: 0
It exits non-zero below 80% so you can drop it into CI. Measured on 2026-10-17 (Baidu / Bilibili /
CSDN): 82% / 97% / 88% before the click-boundary fix, 100% / 100% / 100% after, at ~40ms
per ui.get_tree.
Those three numbers were measuring the wrong denominator. Until 2026-10-19 the tool only
counted the top document: on a page whose body lives in a cross-process iframe it reported
"4 click targets, 100% usable, 0 gaps" while the entire course catalogue was invisible. It now
measures every frame-N it can reach and prints how many frames it could not โ an
unmeasured area inside the denominator is worse than a wrong measurement. Re-measured
2026-10-19: Baidu 100%, CSDN 99% (8 cross-process frames now counted, 2 residual gaps),
and the ่ถ
ๆ course page 82% with the 2 remaining gaps named explicitly. The write-up of this
class of mistake โ a metric that silently excludes the part that matters โ is
docs/POSTMORTEM_FRAME_VISIBILITY.md.
Two things the numbers do not cover, so you do not chase them: an element the page gives no
readable name (image-only links with no alt โ 53% of Bilibili's clickable nodes) can never get a
label without inventing one, and a canvas has no DOM to read at all. Those are genuine boundaries,
not bugs. The full write-up, including why the first measurement of this was wrong by 3ร (inherited
cursor inflates the denominator), is in
docs/AGENT_OPERABILITY_FEEDBACK.md ยง6.
Test & dev
npm test
npm run smoke
npm run capabilities
npm run richtext
npm run network
npm run value
npm run canvas
npm run modeldiff
npm run audit
npm run nav
npm run focus
npm run interact
npm run view
npm run dialog
npm run wrapper
npm run paint
npm run layout
npm run download
npm run multiagent
npm run input_routing
npm run background
npm run flicker
npm run e2e:all
npm run verify:app
npm run realsites
All e2e suites boot a genuine Electron against offline fixtures and exit non-zero on failure.
Together they cover what jsdom structurally cannot: preload integrity, ui.evaluate under a strict
CSP, CDP click hit-testing, multi-tab lifecycle, event fan-out, and the evaluate guard rails.
Each suite proves it is talking to the browser it just started. Before any assertion runs it
calls ui.server_info and compares the returned pid against the child process it spawned; a
mismatch aborts with exit 4 instead of quietly producing results about somebody else's instance.
That gap was measured, not assumed: with an impostor WebSocket server holding the port, a suite
happily sent ui.new_tab / ui.evaluate / ui.get_tree to it and never noticed. Repro:
REPRO_PORT=9799 node e2e/_repro_identity.cjs.
npm run e2e:all also gives every suite its own port, because they share /tmp/ai-browser-e2e-<port>
as the profile and therefore Electron's single-instance lock too.
They all need the WS port free โ stop a running npm start first, or point them elsewhere:
AI_BROWSER_PORT=9333 npm run smoke
They boot their own Electron in an isolated profile (/tmp/ai-browser-e2e-<port> by default), so
they never touch your real ~/.ai-browser profile โ the one holding your logged-in sessions. They
also clean up their Electron on exit, including on Ctrl-C / timeout / crash: an orphaned process
would otherwise hold the port and the single-instance lock, and you would find npm start refusing
to launch with "another AI Browser instance is already running".
What each capability suite proved
npm run view โ the suite for the two things that quietly produce false confidence.
Viewport. A BrowserView can be fully loaded and still show stale pixels, and the only thing
that forced a repaint was switching tabs โ which is exactly why "click the tabs a few times" used to
fix it. It now fires on every navigation signal and on window show/restore/focus. The suite
proves it from the cumulative repaint counter, not from a screenshot: a screenshot needs eyes, a
counter falsifies. It also proves the debounce doesn't self-trigger (a repaint loop would flicker
forever) and that repainting changes no page data.
Verification. ui.diff is only useful if it is right in both directions, so each assertion comes
in pairs: a real change must be reported and an unchanged page must not be. The negative
controls are the point โ a diff that invented changes, or a snapshot that quietly became empty on
error (making every later diff report "unchanged"), would turn all verification into false green.
The suite also pins the failure mode where a mistyped parameter layer made type report success
without typing anything.
npm run richtext โ the deepest suite. Rich-text editors and formatting, two- and three-level
nested menus, required vs optional fields (native required, aria-required, red asterisks),
error and warning surfaces (field-level, form-level, toasts, modal dialogs), radio / checkbox /
select / combobox, tag inputs and Weibo-style topic insertion, and image upload. Every
action assertion is checked against the real DOM, not just the semantic tree.
Two things it changed in the product:
- A click on a button that dismisses itself used to fire twice (the hit-test ran after the
dispatch, found the target gone, and fell back to a second click). Duplicate submissions,
duplicate mentions. Clicks now hit-test before dispatching and no longer fall back.
- Field-level errors used to be invisible โ they are carried by bare
<span>s with no ARIA role and
were pruned as layout. They now surface in context.errors / context.field_errors, scanned
across the whole document rather than only inside dialog containers.
- Three reads used to depend on a container's class name. Red asterisks were scanned only
inside containers whose class happened to contain
modal/dialog/popup/โฆ, so a plain-page
form's required fields were invisible; modals[].fields[] entries carried no id, so an error
read for one field could not be mapped back to it; and auxiliary text in bare
<span>/<div> (character counters, format hints) was pruned from the semantic tree with no
second path at all. All three now sit at the top level of context: required_hints is
scanned across the whole document, fields[] entries are shaped identically in modals[] and
forms[] (id included, verified against the real DOM), and form-adjacent bare-span text lands
in hints โ the semantic tree itself keeps its pruning, so the token cost is unchanged.
npm run capabilities โ typing into every kind of text field (plain inputs, password,
number, textarea, contenteditable, plus readonly / disabled / maxlength โ including
CJK input and 1000-character text), reading page source, capturing response bodies, and editing
the page through ui.evaluate.
npm run network โ that a POST can be captured with its full request body, that headers are
redacted by default, and that bodies paginate instead of being silently truncated. It also pins the
eviction rule: the retained byte budget is global across tabs, so a background tab quietly
filling it used to evict the body the agent was about to read on the active tab โ the request
really happened and the body really was captured, it just got pushed out by someone else's noise.
Eviction now sacrifices non-active tabs first (including the background body being stored), and
ui.network_configure reports active_tab / body_bytes so a future evicted can be attributed
instead of guessed at.
npm run modeldiff โ the suite for the one place ui.diff used to lie. A canvas-rendered app's
DOM is a still photograph: dragging a node or editing a widget repaints <canvas> and moves
nothing the element walk can see, so the DOM-only default snapshot answered unchanged to a write
that demonstrably happened โ including ComfyUI's documented write path, node.widgets[].value,
which moves the DOM by exactly zero bytes. The suite proves the model fingerprint on a self-built
fixture (never someone's live project, where snapping and quantization make "move it back" untrue):
- adding a node โ
verdict: changed, and the diff paths are only model.count / model.fp โ
zero nodes.* and zero text*, which is how the test proves the credit belongs to the model
rather than to the DOM happening to move;
- the ComfyUI case โ changing one widget value with the node count unchanged โ still
changed,
and specifically model.fp without model.count;
- both directions: an untouched page must stay
unchanged, and a plain page with no app object
must never acquire a model field (no false reds from machinery that invented a candidate);
- the model signal must not mask DOM changes โ when both move, both are reported.
Two design points the suite pins, both learned the hard way:
- selection is by what can actually be read back, not by how promising the name looks. A library
namespace scores well on names and has no model to hand back, so returning null is what
disqualifies it;
- the rank comes from the strongest accessor the object has, while the read goes through
serialize() when one exists (it returns JSON-safe data; the live collections are usually
circular). Collapsing the two makes every candidate report serialize, they all tie, and a mere
serializer can outrank the real model โ that bug was caught by the tie-break test, not by review.
Canvas: read through draw calls, not pixels
The semantic tree reports a <canvas> as role: canvas and nothing more โ no text, no pixels.
browse_canvas fixes that without taking a screenshot: a recorder is injected into the
page's main world and wraps the Canvas API, capturing the draw calls themselves.
The point is that a canvas is drawn by code, so the code already knows what it drew. fillText
hands us the literal string โ text inside a canvas needs no OCR:
{
"kind": "2d", "readability": "semantic",
"texts": [
{ "seq": 2, "method": "fillText", "text": "็กฎ่ฎคๆฏไป",
"bounds_canvas": { "x": 20, "y": 40, "width": 120, "height": 30 },
"style": { "font": "20px sans-serif", "fill_style": "#000000" } }
],
"regions": [ { "seq": 3, "kind": "rect", "method": "fillRect", "bounds_canvas": {โฆ} } ]
}
The recorder is a tee, never a takeover: it calls the native API first
(Reflect.apply(original, โฆ)) and only then records, inside its own try/catch. A recording
failure can never change a return value, an exception, this, or draw order.
Two limits you should know:
- The hook installs after a page's first load, so anything drawn during that initial load is
not recoverable.
browse_canvas(operation: "configure", reload: true) reloads with the hook in
place and gives you the complete history. (Root cause: awaited CDP commands hang on a
freshly-created tab in Electron, so installation has to wait for did-finish-load.)
- WebGL is opaque. Vertices, textures and shaders are not reversible to business meaning, and
text is usually a glyph atlas. Such canvases are marked
opaque rather than guessed at. For
that case only, operation: "capture" returns a PNG of the canvas region โ off by default,
explicitly invoked, and it costs your agent's vision tokens.
Disable entirely with AI_BROWSER_CANVAS_HOOK=0.
It is off by default. Wrapping getContext is something the page can see โ one
Function.prototype.toString.call(HTMLCanvasElement.prototype.getContext) and the site knows its
canvas API was patched (measured on Baidu, 2026-11-01). The recorder is the loudest automation tell
this browser carried, and every site paid for it while only canvas apps gained from it. So:
- per tab, on demand:
browse_canvas(operation: "configure", reload: true) installs it and gives
the full history for that page;
- for a whole origin:
AI_BROWSER_CANVAS_HOOK=b.chaoxing.com,excalidraw.com (comma-separated,
subdomains included);
- everywhere:
AI_BROWSER_CANVAS_HOOK=1 โ what v2.4 and earlier did, and what risk controls
noticed.
Boundaries worth knowing before you rely on them
node.value is truncated at 200 characters. That is our limit, not CDP's. When it truncates
the node carries value_truncated: true, value_full_length, and a ready-to-call value_fetch
hint โ use browse_act(action: "get_value"), which is read-only and paginates.
- Password fields expose no value at all โ only
value_sensitive: true. The semantic tree is fed
wholesale into your agent's context, so it should not carry secrets.
js_error is broadcast for every tab (each event carries tabId), so ordering and indices are
not guaranteed. Filter by tabId; do not rely on "the first error is the one I care about".
- A "connection handle" is only used if a real pointer could hit it. Many sites render handles as
pointer-events: none + opacity: 0 decorations (verified on the rhtv canvas: every handle is
pe:none / op:0). Anchoring on such an element would press the node body instead โ so the resolver
self-checks with elementFromPoint and falls back to the element's border midpoint, reporting
via: "edge". If you see via: "edge" where you expected a handle, that is the honest answer:
drag-to-connect is not available at that spot, and the site must wire nodes some other way.
ui.scroll is document scrolling. It does window.scrollBy, so it is a no-op on canvas-based
editors, maps and charts. Use ui.act{action:'wheel'} there.
npm run realsites is table-driven from e2e/realsites/sites.cjs, currently 17 sites across 8 buckets
(search, finance, media, dev, ecommerce, spa, editor, marketplace). The run prints two numbers, and
deliberately never blends them into one:
- ่กไธบๆญฃ็กฎ็ / behaviour rate โ did the browser behave as expected? Sites that require login or
answer with an anti-bot wall count as passing when the wall is correctly detected, because that
means the detection works.
- ๅ
ๅฎนๆๅ็ / content rate โ did we actually read the content? This counts only sites where
the tree came back above the site's
minNodes; a wall is not content.
Reporting a single "success %" would let a correctly-detected login wall inflate the content number.
The run also prints the corpus size, runs-per-site, run count and timestamp, so any percentage in a
report can be re-derived rather than taken on faith.
Layout:
src/main/ Electron main โ ws_server ยท page_manager (tabs, CDP) ยท mcp_server ยท mcp_tools ยท axExtractor
src/preload/ bridge ยท extractor (semantic tree, data-ai-id) ยท actions ยท watcher
src/renderer/ tab bar UI
src/shared/ config (AI_BROWSER_* env) ยท guards (evaluate safety) ยท protocol ยท watchdog
e2e/ smoke_ws.cjs ยท realsites/
tests/ vitest unit suites
skills/ optional higher-level recipes built on the tools
src/shared/config.js is the single source for port, user-data dir, and UA overrides; guards.js is
the single source for evaluate limits, enforced identically on both transports.
Compatibility
| Dimension | Support |
|---|
| Agents | Any MCP stdio client; alternatively raw WS from any language |
| Node | โฅ 18 |
| OS | macOS and Linux โ developed and tested on these. Windows: experimental and untested. It is plain Electron plus CDP, so it ought to build, but no one has run it; expect to debug npm install and the window layer yourself. Please report back either way. |
| Page frameworks | React / Vue / Angular / vanilla DOM โ element locating is DOM-based, not framework-based |
| Editors | Rich editors driven through trusted input rather than per-framework code paths |
| Page types | Static and SPA; dynamic updates observable via the tree, dom_change / state_changed events |
Contributing
Issues and PRs are welcome, especially reproduction cases where the semantic tree gets a page wrong โ
those are the most useful bug reports this project can get.
Questions, "the tree got this page wrong" reports, and agent run logs are best posted in
GitHub Discussions โ that is where the most
useful feedback for this project tends to land.
What we try to hold the line on:
- Keep the core generic. Site-specific knowledge belongs outside
src/main and src/preload.
- IPC stays request-id matched, and CDP sessions stay reference-counted โ tabs leak otherwise.
- No screenshots. If a change needs pixels to work, the design question is upstream of it.
evaluate stays guarded (length cap, no Node identifiers), on both transports at once.
- Agent instructions change when behaviour changes. The MCP tool list,
ws_server.js methods,
and examples/AGENT_INSTRUCTIONS.md must agree; a doc that drifts from mcp_tools.js is a bug.
License
MIT ยฉ Glittering