Tailscode: Coding Agent Remote
Tailscode: Coding Agent Remote is #145 in Developer Tools Free in South Korea and charting in 1 of 30 countries we track.
Updated 24 Oct 2026 · rankings refresh through the day
DeveloperMidgar Oy
CategoryDeveloper Tools
PriceFree
Released
Rating★ 0.0 (0)
Version1.78
Age rating4+
First seen by us
6 Oct 2026
Rating
0.0 ★
0 ratings
Measured
Best rank now
#145
Measured
Tailscode: Coding Agent Remote on the App Store
App details
App ID
6791660932
Publisher
Midgar Oy
On the store since
Jul 2026
Under a year
Minimum OS
iOS 18.0+
iPhone XS and later
Devices
iPhone · iPad
Universal purchase · Game Center
Content rating
4+
Languages
11
EN FR DE IT JA KO PL PT ZH ES ZH
Size
52 MB
Also listed in
Productivity
Where it ranks now
Every top chart it appears in across 30 countries.
| Country | Charts | Rank |
|---|---|---|
| Developer ToolsFree | #145 |
Apps near Tailscode: Coding Agent Remote on the chart
Developer Tools Free, around #145.
Ratings
App Store, worldwide.
Rating
0.0 ★
0 ratings
Measured
Ratings
0
Measured
About Tailscode: Coding Agent Remote
Send a prompt to Claude Code, opencode or Oh My Pi from your phone, pocket it, and watch the turn finish on your Lock Screen. Approve the risky command, answer the agent's question, read the diff — over your own Tailscale network, with no relay, no account and no analytics. Free and open source.
TRY IT BEFORE YOU WIRE ANYTHING
A built-in demo walks every screen with sample conversations. No server needed.
WHAT YOU NEED
A Mac or Linux machine on your tailnet (Tailscale is free for personal use) running one of your agents: opencode, Claude Code through the open-source claude-bridge, or Oh My Pi through the open-source omp-bridge. Set-up is three verified steps.
THE TURN, LIVE ON YOUR LOCK SCREEN
• A Live Activity per conversation: what it is doing, for how long, and how many tools it has run.
• An approval request alerts you; a finished turn lingers with its outcome. Tap to land in the exact chat.
• Updates arrive by push while the app is suspended.
A NATIVE TRANSCRIPT, NOT A TERMINAL
• Streaming text written at the model's own speed, with thinking and tool runs folded into readable groups.
• Diffs, commands and their real output inline; syntax-highlighted code with byte-exact copy.
• Allow once, always, or deny without leaving the chat. Agent questions become tappable cards, and a failed turn says what happened and offers to try again.
• One quiet row of facts — context, spend, branch, agents out — that steps aside when there is nothing to say.
• Queue the next message while a turn runs, edit it before it goes, or stop the turn on the server.
• Every picture the agent hands you, in a gallery you can zoom, save or share.
EVERY MACHINE ON ONE BOARD
• All your servers' conversations in one list, live status first, grouped by project.
• Read the repository before you trust the change: branch, staged, changed, untracked, and the diff of any file.
• Subagents dock inside the turn that spawned them; a compaction is drawn as a seam with what it kept.
• Slash commands from the server's own catalog, per-message model and reasoning effort, forking.
KNOW WHAT IT COSTS
• Every conversation priced, every month totalled across machines — by model, project and tool.
• Plan limits and quotas for Claude, Grok, Ollama Cloud, DeepSeek and more, on Home and in a widget.
PICTURES AND CLIPS, ON YOUR OWN MACHINE
• Describe an image or a short clip in words; it renders on your own machine and arrives in the app.
HAND OFF THE ROUTINE WORK (BETA)
• A cheaper model tries first and a verifier decides. Nothing lands until it passes.
YOURS, END TO END
• Point-to-point over your tailnet. No relay servers, no account, no analytics, nobody reading your code.
• Programmatic UIKit, Swift 6, Liquid Glass on iOS 26. Eight themes, dark mode, Dynamic Type, haptics.
• Open source under GPL-3.0 — the app, the engine, and both bridges.
FREE, WITH AN HONEST PRO
The free app is the complete core: one server, full chat, approvals, attachments, models, forking, and Live Activities. T
TRY IT BEFORE YOU WIRE ANYTHING
A built-in demo walks every screen with sample conversations. No server needed.
WHAT YOU NEED
A Mac or Linux machine on your tailnet (Tailscale is free for personal use) running one of your agents: opencode, Claude Code through the open-source claude-bridge, or Oh My Pi through the open-source omp-bridge. Set-up is three verified steps.
THE TURN, LIVE ON YOUR LOCK SCREEN
• A Live Activity per conversation: what it is doing, for how long, and how many tools it has run.
• An approval request alerts you; a finished turn lingers with its outcome. Tap to land in the exact chat.
• Updates arrive by push while the app is suspended.
A NATIVE TRANSCRIPT, NOT A TERMINAL
• Streaming text written at the model's own speed, with thinking and tool runs folded into readable groups.
• Diffs, commands and their real output inline; syntax-highlighted code with byte-exact copy.
• Allow once, always, or deny without leaving the chat. Agent questions become tappable cards, and a failed turn says what happened and offers to try again.
• One quiet row of facts — context, spend, branch, agents out — that steps aside when there is nothing to say.
• Queue the next message while a turn runs, edit it before it goes, or stop the turn on the server.
• Every picture the agent hands you, in a gallery you can zoom, save or share.
EVERY MACHINE ON ONE BOARD
• All your servers' conversations in one list, live status first, grouped by project.
• Read the repository before you trust the change: branch, staged, changed, untracked, and the diff of any file.
• Subagents dock inside the turn that spawned them; a compaction is drawn as a seam with what it kept.
• Slash commands from the server's own catalog, per-message model and reasoning effort, forking.
KNOW WHAT IT COSTS
• Every conversation priced, every month totalled across machines — by model, project and tool.
• Plan limits and quotas for Claude, Grok, Ollama Cloud, DeepSeek and more, on Home and in a widget.
PICTURES AND CLIPS, ON YOUR OWN MACHINE
• Describe an image or a short clip in words; it renders on your own machine and arrives in the app.
HAND OFF THE ROUTINE WORK (BETA)
• A cheaper model tries first and a verifier decides. Nothing lands until it passes.
YOURS, END TO END
• Point-to-point over your tailnet. No relay servers, no account, no analytics, nobody reading your code.
• Programmatic UIKit, Swift 6, Liquid Glass on iOS 26. Eight themes, dark mode, Dynamic Type, haptics.
• Open source under GPL-3.0 — the app, the engine, and both bridges.
FREE, WITH AN HONEST PRO
The free app is the complete core: one server, full chat, approvals, attachments, models, forking, and Live Activities. T
Latest updates
1.78
New:
• Notifications say what happened and answer back. A finished turn shows how long it took, how many tools it ran, what it changed and the first of what it said; a failure shows the error and offers Try again; an approval shows the exact command and Approve asks for Face ID; a question shows its options as buttons. Reply from the Lock Screen to start the next turn, and pull a notification down for a full card. Servers on claude-bridge 1.15 send all of this when the app is closed.
• Home is one board. A sentence at the top says what it all adds up to — who needs you, what is working, or that all is quiet — over one vertical list: Needs you, Working, Pinned, Saved, Recent. Every chat is the same row everywhere, with a line only when something happened, and a waiting chat shows the command or question it is waiting on. On iPad and iPhone Duo, Home beside the chat list becomes Today: each waiting question in full, and your quotas.
• FLUX 3 Klein paints and edits. The Fast engine now runs FLUX 3 Image Klein: finer detail, lettering that spells what you asked for, and edits that can work from several pictures at once, named image1, image2 in your words. Your ComfyUI machine needs version 0.41 and the new model files; the machine sheet lists anything it is missing.
• Watch the app your agent is changing. A Mac running previewd builds it, runs it on a simulator and streams the screen. Open it from the conversation, see each change land, and when a build fails keep the last good picture with the compiler's first error and a button that hands it to the agent.
• A video render outlives the app. It is written down before it starts, so quitting or reinstalling no longer loses it: the next launch finds it on the machine and follows it to the end.
Changes:
• The video button is a light. A ring round its edge shows the machine waking, the queue, how far the render has got, saving, and a clip that landed or a render that broke until you have looked at it.
• Stop names its own render, so it never interrupts somebody else's job on a shared machine.
• Continue it shows which clip it is continuing, and a clip is saved under its words and seed.
Fixes:
• The attach button no longer disappears when the model cannot read pictures: Files still attach, and Photo Library says why it is off.
1.71
Fixes:
• Opening the app after hours away no longer walks the screen through everything your servers did meanwhile: it reads where things stand once instead of replaying the log, and a burst of list changes lands as a single move.
• An answer that lands a table no longer quits the app: the card standing in for a table while it is still being written hands over to the finished table in the same place, and nothing moves under your thumb.
• A queued message is sent exactly once, however many places wake up on the same conversation — a phone and its background watch can no longer take the same message twice.
Changes:
• What you decide about a chat now follows you between devices through your own servers and nobody else's: read and unread, pins, the archive and saved chats are kept by claude-bridge 1.14 and omp-bridge 0.8 (update them in Settings › Software) and show up on every device within a second. A chat open in front of you stays marked read as it grows.
• The chat menu gains Pin, Mark as unread and Archive.
• Made for iPhone Duo: opened out to its inner display, the workspace shows your sessions beside the conversation, and the conversation keeps to one page while tool output, tables and repository state open on the other.
• Held like a laptop, the transcript stops at the fold while the composer, chips and effort rail stay on the base.
• Grids use an even number of columns so nothing sits on the fold, and nothing the app draws beside the side bar hides under it.
1.68
Novidades:
• A lista completa de modelos é o mesmo seletor do controle na caixa de mensagem. Seus pares fixados de modelo e nível vêm primeiro, e cada linha mostra o nível em que uma escolha rodaria, desenhado com as mesmas barras e a mesma regra de transferência.
• A faixa de esforço sobre a lista nomeia o modelo em uso e diz se muda esta conversa ou a próxima; toque ou deslize até um nível, com um tique a cada um.
• Uma estrela em uma linha fixa aquele modelo no nível mostrado; os pares fixados que vivem em outra máquina continuam listados, com a máquina que os executa.
• Os servidores são as abas e os provedores são os chips embaixo delas, e "uma escolha aqui inicia uma nova conversa em …" é dito uma única vez acima da lista em vez de em cada linha.
• Aberta pela Home, por uma conversa ou pelo modelo padrão de um servidor, a lista diz o que uma escolha vai fazer antes de você fazê-la.
• Modelo e esforço são um único controle na caixa de mensagem, em todas as conversas e na Home: um ponto na cor do modelo, o modelo, a palavra do esforço e cinco barras de calor.
• Toque na metade do esforço para abrir os níveis como um trilho e tocar em um, ou deslize pela metade do esforço para percorrer os níveis, com um tique a cada um. Deslize a metade do modelo para alternar entre seus pares fixados de modelo e nível.
• Fixe um modelo e um nível juntos. Os pares fixados encabeçam o menu rápido, e um par só é oferecido onde aquela máquina realmente consegue executá-lo.
• Todo provedor e todo modelo local recebe o mesmo tratamento: níveis como think e nothink, fast, none ou orçamentos numéricos são lidos, ordenados e desenhados no medidor. Trocar para um modelo que não tem o seu nível o move para o mais baixo mais próximo e avisa você.
• Os modelos de outras máquinas ficam agrupados no menu rápido. Escolher um aponta a caixa de mensagem para aquela máquina e avisa, e as linhas de máquinas abaixo do chip de destino mostram o que cada uma vai executar.
• Modelos locais e de gateway mantêm o próprio nome e cor: uma versão do Qwen com nome de Claude não é mais desenhada como Opus.
• Na faixa de imagens, manter pressionado "Gerar" ou "Editar" (ou "Enviar" da Home) oferece um briefing escrito pelo assistente da máquina que pinta.
Mudanças:
• Nada na lista é mais cortado: nomes de modelos, ids, notas como "esgotado, reinicia em …" e a máquina em que um modelo roda quebram para outra linha, e nos tamanhos de texto de acessibilidade os controles acima da lista rolam junto com ela em vez de cobri-la.
• Manter pressionada uma linha na lista de modelos mostra um cartão: o tamanho do contexto, o que ele lê, os níveis que aceita, o que seria do seu nível e o que uma troca relê.
• De xhigh para cima, uma linha colorida corre pelo topo da caixa de mensagem, e o ultracode a envolve em um arco-íris.
Correções:
• Uma linha cujo provedor ou limite mudou mantinha a altura antiga e cortava o texto; agora ela se redimensiona.
• As últimas linhas de uma conversa não ficam mais escondidas atrás dos chips sobre a caixa de mensagem, e uma conversa abre no final e fica lá enquanto as linhas se assentam.
• O botão "Usar" do cartão de aprimoramento agora lê bem sobre o fundo de vidro, e a caixa de prompt do estúdio tem um botão de limpar.
Store changes
What Tailscode: Coding Agent Remote changed on its store page: name, icon, screenshots, price, size, languages, requirements.
App got bigger
40 MB → 52 MB (+30%)