仓库 →

Web UI

Besides the terminal TUI, AtomCode ships a built-in browser interface: type /webui in the TUI to launch it, then chat, browse session history, add/edit/delete model providers, and upload images in the browser — and use /sync to mirror one session live between the terminal and the browser. It reuses this machine's login, models, and session history, so there's nothing extra to configure.

Start & stop

Run these in the AtomCode TUI input box:

# Launch the webui and open the browser (binds 127.0.0.1:13457 by default — local only)
/webui

# Stop the webui server
/webui stop

On launch, AtomCode starts a local HTTP server and opens your browser to a URL like http://127.0.0.1:13457/?token=<one-time token>. The token in the URL is the credential — it's equivalent to a password, so don't share it. The current TUI session is also attached to live sync automatically (see Live sync across devices below).

Localhost only by default

The webui binds 127.0.0.1, reachable only from this machine. To open it from a phone, do not expose it with --host 0.0.0.0; use the 蒲公英 virtual-LAN approach instead — see Remote Access.

What the interface offers

The browser UI brings the terminal's capabilities into a graphical interface:

AreaWhat you can do
SidebarSession history grouped by project, search sessions, start a new chat, rename / delete sessions; collapses to an icon rail (a drawer on mobile).
Model selectorSwitch provider / model right under the input box; same-named models are disambiguated with a provider tag.
Model configManage provider accounts and multiple models under each account, including protocol, base URL, API key, context window, and the default model.
SettingsTheme (light / dark), language (中 / EN), model config, and the remote-access entry.
Image attachmentsPaste or pick images to send with a message (2 MB each); non-vision models fall back to VL; thumbnails show in history.
Tool executionTool calls show their arguments and output inline, expandable line by line, both live and in history.
Attach menu (+)Upload an image, pick a file for context, or insert a Skill.
Working directorySwitch the working dir, browse folders, create a new folder, set a default working dir.

Live sync across devices

Behind the webui is a LiveSession: one session can be open in the terminal and multiple browser tabs at once, and every input, streamed AI reply, and tool result is broadcast live to all connected views — a viewer that joins late first receives a snapshot replay.

This makes "start in the terminal, watch progress on a phone / tablet" — or several people watching the same agent session — possible.

Approval modes

A pill in the bottom bar sets how the agent's actions are gated — the browser mirror of the terminal's approval modes. The default is Build.

ModeBehaviour
Build (default)Interactive — every file edit and command asks for approval before it runs.
Accept EditsFile edits are auto-approved; commands still ask.
PlanRead-only exploration — write and execute tools are blocked so the agent proposes a plan first.
Bypass (免审批)⚠ Auto-approves everything, including edits and commands. Use with care.

The mode is process-wide and broadcast over the live channel, so switching it in one tab updates every connected view. It is not written to your config — it resets to Build on restart.

When the agent needs a decision from you mid-task, an interactive question card appears (single choice, multiple choice, or free text) and the turn pauses until you answer. See Interactive Questions for the full behaviour.

Remote access

Want to open the webui from a phone without exposing it publicly? Use a 蒲公英 (Oray PGY) virtual LAN: bind the server to the virtual IP with /webui --host <virtual IP>, then scan the QR in the Remote Access panel. Full walkthrough in Remote Access.

Next