The Mac mini shows the cloud brain, whose bots work on the brain's own
computer and borrow only this Mac's screen, browser and apps. Its local
box still ran, and the Lima VM under it had grown to its whole 6 GB: the
Mac never gets back memory a VM once used.
- On a screen the box stops after 2 idle minutes, and the Lima VM too when
nothing else runs in it. probe() no longer starts the VM there, and the
volume holder and scheduled updates run on brains only. Becoming a brain
again starts both (probe/ensure_running already wake the VM).
- Screen mode is decided from the settings before the box loop's first
look, which used to start the VM at launch.
- gvisor-vm.sh: 4 GB instead of 6 (box capped at 2 GB), and the VM's
ModemManager, udisks2 and multipathd are turned off.
Verified on this Mac: box and VM stopped by themselves 2 minutes after the
app started; the VM process (4.4 GB plus compressed pages) is gone.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha5F5gJt93t3yEx3XcS
Each bot keeps a work log (oplog/bot-<id>.jsonl, after pi's durable-harness design, cut down):
before something happens a line says it is about to — the turn, each model call, each step once
its checks passed (with the arguments it runs with and whether it may run again), each message
typed mid-turn — synced to disk first. When the turn ends the file shrinks to the messages still
waiting, usually nothing.
On the next start after AnyBot was killed mid-turn, the log puts the chat right before anything
runs: the message the turn answered comes back if the chat lost it; a step that was running and
reaches outside (a text, a click, a file, a published site) shows as 「可能已經執行了」, both to the
person and in the result the bot reads — no longer as "not allowed"; a step that only looked shows
as cut off; messages typed mid-turn that never reached the bot go back into the chat. The chat is
saved, then the log closes the turn. A turn the person didn't stop ends with a 「繼續」 card (what
it was doing, what may have run, the messages put back); it goes on only when they press it — in
the window, on a screen of the brain, or on the phone — from where its steps stand, never running
a step that may have run again. Pressing stop is on disk at once, and a stopped turn stays
stopped.
Also in the turn loop:
- 自動審核 that doesn't answer (or answers something that isn't a verdict) asks the person; in
直接操作 mode it used to let the step through unchecked.
- "Too long for this model" folds older messages into a summary and asks the same step again,
once per thing the person said, instead of ending the turn.
- Folding keeps the person's chat whole: the summary goes in at the fold and the model reads from
the newest summary on (it used to delete what it folded).
- A step moved to the chosen computer runs there, but the chat keeps the call as the model wrote
it; the result says where it ran.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha5F5gJt93t3yEx3XcS
Every warning `cargo clippy --all-targets` gave (50 on macOS, 8 more only on
Linux, 1 in the relay), fixed without changing what anything does:
- long types get a name (Peer, Members, Imported, Joining, Mention, Stream…);
- the two big enum variants are boxed (the vault's login plan, joining an
account);
- a test now waits for the copy it relaunched (it left a zombie behind);
- a hint's format had a dead `if` whose two branches were both "";
- the rest is what clippy suggests: sort_by_key, as_chunks, is_none_or,
is_multiple_of, while let, from_ref, next_back, struct init, no casts to
the same type.
Checked: cargo test (177 macOS, 181 Linux), relay tests (11), remote_e2e
28/28, and the live Linux test (X11; Wayland clicks, keys, Chinese typing,
scroll and screenshots).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
A new mobile/index.html in the desktop's (and Grok Bot's) shape: the sidebar
with its sections and folders, the chat with steps, thinking, reactions, quotes
and the approval card, 對話詳細資訊, Bot 設定, routines, pages, computers and
設定. Each action goes to the desktop's own code on the app's thread
(api/act/<what> -> App::phone_act): appctl, set_pinned, restart_bot,
toggle_reaction, box_task, channels_restart and the rest. No new rules.
Keys, channel tokens and the vault never reach the phone; a model key can only
be written. Admins keep what the phone always let them do; making, changing or
deleting bots, routines, memories, pages, folders and settings stays the
owner's. The state the phone polls now carries the sidebar's section order.
Checked by using it on a preview brain: routines, memories, templates, folders,
keys, signing another phone out, approvals and a chat with a fake model.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
- box_numbers_only_on_what_is_seen is ignored again (a test inserted before it in cbada6b took
its mark: every cargo test drove the real box), and the path test runs
- gvisor-vm.sh restarts the VM's Docker only when runsc was just registered (a restart stopped
Bot 的電腦), and `${var}` before full-width text (bash read 「）」's first byte as part of
the name and stopped)
- a scheduled box update and a PDF's name use the person's time zone (a server keeps UTC)
- 容器隔離 lists 標準 before 強隔離
- screenshots of real data can open 設定 › 電腦 (ANYBOT_SHOT_VIEW=computers) and scroll
(ANYBOT_SHOT_SCROLL)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
容器隔離 in 設定 › 電腦: standard (runc, the container is the only wall, Chromium runs
--no-sandbox) or hardened (runsc: a virtualized kernel, all capabilities dropped but the few
the desktop needs, ANYBOT_BOX_SANDBOX=1 turns Chromium's own sandbox back on). Box image v7.
deploy/mac/gvisor-vm.sh makes a Lima VM with Docker + gVisor for a Mac (started at login),
gvisor-migrate.sh moves the box's files and logins there.
Checked and finished before committing:
- the hardened choice is offered only on a Docker host that has runsc; a box set to it on a
host without it opens the standard way and says so (it used to not start at all)
- the settings row shows what the box really runs on, and when 更新 is needed
- no swap only under gVisor (a standard box keeps Docker's default)
- the migrate script sees the running Mac app ("AnyBot", not "anybot")
- the VM script starts an existing VM by name, checks runsc and the kernel from the Mac
- the version test says 7
Real run in the Lima VM: desktop, VNC, numbered controls, xdotool and screenshots work; no
Chromium process has --no-sandbox, renderers run with seccomp and their own namespaces.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
- A job of five or more real steps is looked back on after the answer: the short way that
worked becomes a skill (or improves the one it followed); the reply says so. The prompt has
the bot check its skills before starting.
- Upload, download and PDF on Bot 的電腦's browser look for and save files in the box, not on
the brain (a picture in a Threads post took 24 steps).
- The bot's browser keeps the six tabs used last (19 Threads tabs had filled the box's 2 GB).
- Words name the control, not the box around it: a form's 「Customer name:」, 「Large」 and
「Submit order」 used to land on the <p> holding them and do nothing.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
Both cloud brains had 「Etc/UTC」 as the time zone (the server's, set when they were made), so pages
said 「今天 01:03」 for 09:03 and a routine for 9 in the morning would run at 5 in the afternoon. The
phone now says where the person is; a brain still on a server's zone takes it (a zone the person
chose stays). Page times use the person's zone, not the computer's.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
The phone page was bare: one row per bot, a chat listing every step, a menu with four lines.
- Home: the main bot large at the top with its model and last words, the other bots with times,
then its computers (own box and the account's, online or not, 看畫面), the newest pages and the
routines with their next run.
- Chat: the bot's name opens its settings — model (chat models only), computer, past conversations
(restore), regenerate, new chat. A turn's steps fold into 「已完成 N 個步驟」 when done (the newest
three stay while it works); copy and regenerate under replies; four ready starts in a new chat;
a jump back to the newest message.
- Menu: 外觀 (follow the phone, light, dark).
- API: api/state carries pages and models; each bot its model, computers, routines, past
conversations; POST api/bots/{id}/set | regenerate | restore. The home's last line skips errors.
Checked on a local copy of the brain's data (cut off from the account and Docker) at iPhone size.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
From looking at the real phone page after the fixes: a long command squeezed its step's name into
one character per line (執/行/指/令), and sending a file showed as 「工具」. The name keeps its width,
the detail is cut with an ellipsis, and send_file, react and view_demo_step have names; the window
says 「正在傳檔案給你」 instead of 「正在記下來」 while a file is sent.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha2RVfSYmrhqNnqx9Z4
- computer_use_batch: up to 8 planned actions run in one docker exec (steps chained with && and a
done-marker each), the first failure stops the rest, one picture comes back at the end. Typed
text rides inside the script quoted (one stdin for the chain). The prompt tells the model when
to use it (a form whose fields are all visible) and when not to (step 2 needs step 1's screen).
- The box waits for the screen to stop changing, not the clock: two matching small probes (~60 ms
each) mean settled — ~160 ms on a still screen where every step paid a fixed 500 ms, and a page
mid-load is waited for (up to ~0.9 s) instead of captured mid-change. The picture is JPEG, and
the a11y read runs in parallel with the capture (look ~307 ms; two steps with pictures 1102 ms).
(SETTLE_SH is a group command: dash needs ';' after it — found by box_screen_is_exact.)
- The home volume (every bot's logins) is never one command from loss: snapshots keep generations
(last 7 days, then one per week; the old single snapshot migrates by file date), Reset and
Restore save the running box first and refuse to wipe if saving fails, a box built on an empty
volume re-fills itself from the newest snapshot, and a sleeping holder container keeps the
volume attached so `docker volume prune` can't take it. make doctor shows volume and snapshot
state; the 電腦 card shows the box's average step times and says resets save first.
- box_batch_in_one_round_trip (ignored): three typed steps, ASCII and Chinese, land in one trip.
On the real box after upgrading v3→v5: box_update_keeps_files (files survive, snapshot 2 代),
box_numbers_are_exact, box_screen_is_exact, box_end_to_end, box_traffic_via_mac pass; 155 unit tests.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Unused (found by taking away the dead-code allowances; nothing else used them, tests aside):
computer::specs, quiet_button, the never-made Poke::Spin, ten icons and their SVGs, the
theme's chrome/bubble_agent colours, ImportRow.line, voice's multipart/transcribe/speak
wrappers, and the old keychain writers vault::save/remove/index_add with their live test
(the vault store replaced them; reading old keychain entries for the import stays).
One copy each: percent-encoding (httpd::url_encode, was four), tool arguments (tools::args_of,
was three), the WebSocket handshake (httpd::accept_websocket, was three), the read pacing
(wire::Pace, was two: relay and app), docker with input and a time limit (dk_with_input, was
two). Docs: FEATURES §看畫面 (VNC), protocol (v* frames, /screen, tickets), architecture.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
- The brain looked the account's computers up once a minute: for up to a minute after the Mac
came on, 「我的電腦」 was unknown and steps went elsewhere. Now every 15 s, and at once when a
message comes from a computer it doesn't know yet.
- A step naming a computer that is off says so in words instead of running on the chosen one
with a note that the person hadn't asked.
- Snapshots: tar's 'file changed' (the open browser) is not a failure; browser caches are left
out; ten minutes for a large home folder.
- box_end_to_end clicks the terminal where it opened; restore only with ANYBOT_TEST_RESTORE=1.
- deploy/test/remote_e2e.py: account server + headless brain + hands + scripted model, 27 checks
(computers, redirect, agent-desktop on the hands, hand-off 3 ways, phone view, sync copy,
edits, hands offline/back, brain restart, clear). anybot --sample-state for such tests.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- hand_over_computer (the original's box hand-off card): instruction, live screen with 接管,
跳過 / 我完成了 / 接管; 我完成了 also in the viewer; a typed message answers it too. Header,
sidebar and notifications say 等你處理 / 「{name}：需要你」; the phone shows it with 接管.
- Mac: the content reaches the top (no grey title bar); the top strip drags the window.
- Panel 電腦 card: each line stops before the picture; the brain's name on its own line.
- Viewer: buttons first, the title ends in … when narrow; the picture is centred.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- No idle pause: an asleep box is woken; its files are saved once a day instead of before sleep.
- A headless brain offers no Local computer; attachments it receives go into the bot's own one.
- 「你的電腦」 kept by older versions means the bot's own computer; only an explicit choice moves it.
- The composer chip moved to the panel's 電腦 card (做事的電腦).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- A bot's own computer is 「<bot> 的電腦」; this one and the account's others go by their names.
The server brain picked 你的電腦 by sorted host id, so a desktop left on the server won.
- 「我的電腦」 is the computer the person typed on (the relay names it); unknown means ask.
- A step moved back to the chosen computer tells the bot so.
- Composer chip and bot settings choose the computer by name; a screen asks the brain.
- A screen's 電腦 card and viewer show the brain's computer, not this one's box.
- A screen's chat copy that falls short asks for everything again instead of appending;
清除聊天記錄 on a screen clears the brain's chat.
- Model requests to a private address go through the person's computer first.
- Phone typing on the box sends the text the tool reads.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- On a server brain whose hands are the person's computer, 你的電腦 is that computer;
the server itself is 大腦伺服器 (its browser too), so 「我的 Mac」 means the Mac.
- A brain with its own hands no longer lists the account's other brains as computers.
- 查看電腦 lists the computers the bot really has, with their real names.
- Phone page: with several brains on, it opens the one the account's computers use.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- A new install (desktop or anybot --serve) starts with no bots; the main window shows
「歡迎使用 AnyBot」: connect a model, make the first bot, or sign in.
- Old data whose five sample bots were never used starts empty too.
- Signing in syncs right away: an online brain of the account is used and this computer's
bots are moved there; otherwise the backup's missing bots are taken in and backed up again.
- The five sample bots remain only for screenshots and tests (State::samples).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- write_page / read_page / list_pages: Markdown pages with versions (last 10 kept), per bot;
the reply gets a card (title, fading preview, page icon, 頁面 · 更新時間, 最近更新), and
[標題](page:ID) links open the page
- The page opens large: summary, what changed, the version picker, 複製 / 存成檔案 / 刪除;
listed under 資料庫 in the right panel
- Page blocks for richer pages, in the chat's Markdown too: ```stats tiles, ```steps progress,
> [!NOTE]/[!TIP]/[!WARNING]/[!IMPORTANT] call-outs (with tables and Mermaid charts)
- Phone: the card in chats, page links, a page view with the same blocks; charts drawn by the
AnyBot as SVG (GET /api/pages/<id>[/chart/<n>]); members may read pages
- Bots are told to make a page for things to track and to update it from a routine only when
there is real news
- Screenshot views: ANYBOT_SHOT_VIEW=pagecard / page
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uirha3oEtWeHh58zA7ErHa
- 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
- 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
AnyBot Dev
王性驊