The core: the bot works the computer; a person watches it like a colleague, and takes over
when it needs them. VNC is made for that (only what changed, every mouse move and key, touch on
phones), so the pictures sent one by one go, and with them their own input path.
- vnc.rs: a VNC proxy to the box's x11vnc through one docker exec (a Python bridge that ends
with either side). It signs in to the box with the box's own password (its VNC_PASSWORD) and
offers the viewer no password, so the password never leaves the brain. The person's clicks
and keys make the bot's steps wait until 8 s after they stop; text typed in the viewer's box
(any language) is pasted in the box.
- Account server: /screen (the viewer page) and /novnc.js (noVNC 1.6.0, MPL-2.0, bundled);
/relay/vnc/<host> takes the browser's WebSocket (account session, or a 10-minute ticket the
app asks for with POST /relay/screen-ticket; owners and admins) and carries it over that
AnyBot's lasting connection (vopen / vdata / vtext / vclose). Both ends of that connection
wait 2 ms instead of 40 ms to read while things move: a request and its answer took up to
160 ms more than needed.
- Phone page: 看 Bot 的電腦 and 接管 open the viewer page (also on the local network: /api/vnc on
the AnyBot's own phone server). This Mac's own screen moved to the ⋯ menu.
- Mac app: 看畫面 opens the viewer in the browser (a screen of a brain: the brain's computer by
ticket; else this computer's box, noVNC straight from it). The in-app picture viewer, the
live JPEG stream, the person's click/move/scroll/key endpoints and the input shell are gone.
- Opening a Mac app uses LaunchServices (`open -a`): agent-desktop's launch waited on the window
through accessibility and failed without 輔助使用 now and then.
Measured on this Mac (made-up account, local relay + headless brain + the real box): viewer
signed in in 0.4–0.7 s, a request and its answer through relay + brain + box 25–58 ms median;
headless Chrome shows the desktop live in /screen. remote_e2e 28/28 ×2, 149 unit tests, relay 11.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- One lasting docker exec takes the desktop as a JPEG inside the box and sends a picture only
when it changed (quicker while it changes, slower while still). Viewers ask for the picture
after the one they have and get it at once. It was one exec per picture (a 1 MB PNG decoded
and encoded again on the brain) and a fixed 0.7 s / 1 s pause: about one picture a second.
Measured on the Mac's box: first picture 45 ms, ~90 KB (was ~1.1 MB), 9–19 pictures a second
while it changes; viewers take at most ~8 a second over the network.
- The loop in the box ends the one before it, ends itself when a write fails ("0" lines while
still) and is ended when nobody watched for 10 s (ending docker exec on this side left it
running in the box).
- The person's clicks and keys go through one lasting shell in the box (text as base64), not a
docker exec each.
- Answers over the lasting connection keep their headers (the relay dropped them): a picture's
number reaches the app. JPEG/PNG/PDF/zip bodies are no longer deflated again.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- New icon: the bot's cloud body and slanted eyes (as in the app's avatars) on a dark tile —
the Mac/Linux app, browser tabs, iPhone home screen (PNG: it ignores SVG), Android and
notifications. The web had its own ring-and-dot.
- anybot --write-icon out.png size [file.svg] draws any SVG (for the web PNGs).
- Phone: lists that reach the bottom keep their last row above the home bar and Safari's
toolbar (it looked cut off); bots show their shape, colour and eyes instead of a letter.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- install.sh (curl | sh): app, hands, server and deps modes; installs system packages
(right names per release, e.g. libasound2t64 on Ubuntu 24.04), Rust via rustup (1.95+),
Docker for the server; limits parallel compiles on small machines
- Server Docker image: add the ALSA build/runtime packages (the build failed), cache the
cargo registry and target between rebuilds, JOBS build arg
- 加一台電腦 now gives a line that installs AnyBot on a blank computer before joining it
- Makefile: make deps installs Rust too, make doctor, clear message when Rust is missing/old
- README rewritten: one line per use, getting started, update/remove, troubleshooting,
deployment options; docs/install.md and multi-device.md follow it
- Tested on fresh ubuntu:24.04 (app) and debian:12 (curl | sh hands) containers
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
- .gitea/workflows/release.yml: on a v* tag, a Linux runner builds and
packages the Ubuntu, headless and server bundles; a Mac runner makes
AnyBot.app. Both attach their files to the tag's release.
- deploy/ci: the Linux build image (Ubuntu 22.04), packaging, release
upload, runner settings, and a server bundle that runs the prebuilt
binaries (no compiling on the server).
- deploy/mac/bundle.sh: AnyBot.app with its icon, signed ad hoc, zipped.
- relay/Dockerfile: copy src/wire.rs too (the relay needs it since the
lasting connection).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
- Ticking 建立新帳號 for an account that already exists signs in with it;
when that fails too, the message says the server has an account and
how to reset a forgotten password.
- anybot-relay --data DIR --reset-password NAME (only while the server is
stopped; asks twice, not shown; signs out that account's phones).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
- 加一台電腦 (phone menu and the app's 大腦 card) gives a ten-minute,
one-time code and the line to run: anybot setup <address> <code>. The
new computer joins as hands for that brain with no password and nothing
to answer, starts with the computer and checks the brain sees it.
- anybot setup without arguments is one screen: address and code (a pasted
line fills both), or the account and password instead. No role, name or
confirm questions; a brain is asked only when there are several.
- Hands computers are no longer offered as brains.
- The server setup asks only the domain, account and password.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
- anybot setup: a full-screen terminal guide (role, name, account server,
account, which brain) that saves the settings, installs a systemd user
service (with a virtual screen when there is none), and checks that the
account server and the brain see the computer. Flags for scripts.
- Hands can be limited to one brain; the account server says which AnyBot
asks. Choosing a brain in the app does the same.
- deploy/server/setup.sh: domain, account, sign-ups and keys step by step;
writes .env and Caddyfile, starts everything and checks HTTPS. The
server's brain creates the account on first start.
- deploy/linux/hands.sh installs what's needed and opens anybot setup
(no password kept in a file any more).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
- Each AnyBot keeps one WebSocket to the account server (pinged, reopened
within a second when cut). Requests come down it at once; calls to other
AnyBots of the account (brain sync, hands) go up it. Frames carry raw
bytes, compressed when that saves space. HTTP long-poll stays as fallback.
- The account server knows at once when an AnyBot goes away.
- Edits to lists and maps go item by item, so two computers editing one
list keep both changes.
- Screens fetch chat files from the brain, get model lists through the
brain's keys, and show the brain's computer as the brain's.
- Moving this computer's bots skips starter bots the brain has and bots
already moved.
- The phone goes to the brain instead of a computer that shows it.
- deploy/linux/hands.sh: a Linux computer (with or without a screen) as
hands, kept running by systemd.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
- One worker sends edits, messages and actions to the brain in order.
- Edits carry a number; the brain says which it has, and a screen replays
the rest on top of newer settings so typing isn't undone.
- A message or edit that didn't arrive makes the screen fetch everything again.
- An older copy of a routine can't reset when it last/next runs.
- Network and server failures read as words (no HTTP codes), naming what
can't be reached; the account server notices a closed AnyBot in 8s.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
- Brain answers /api/sync (per-screen deltas of settings and messages),
/api/sync/edit (small edit operations) and /api/sync/act (chat actions).
- Relay forwards host-to-host sync requests within one account (role mirror).
- Desktop: choose a brain in 手機與帳號; its own bots are kept aside; offline
shows the last copy read-only and reconnects by itself.
- Keys and tokens stay on the brain (redacted and restored on edits).
- Browser tools can run on another computer of the account (computer arg).
- anybot --serve: ANYBOT_DEVICE_LINK=1 and ANYBOT_BRAIN=名稱.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
Rust/egui rebuild of Grok Bot as of 2026-11-04: chat with streaming
providers (xAI, OpenAI, Claude, Gemini, OpenRouter, OpenCode Go, Ollama,
custom), tools and approvals, the bot's Docker computer, computer use on
macOS / Linux X11 / Wayland, AnyBot's browser with a full DevTools-based
toolset, the encrypted vault, pinned grid and sidebar sections, Markdown
with Mermaid diagrams, phone access through the relay, and the Linux
build and test scripts.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
王性驊