AI.news
主页教程研究工具模型AI创业讨论新闻每日简报WIKI🚀 创业库★ 投稿
AI+医疗机器人教育金融能源健康娱乐思考

Chatcode – Remote control for Claude Code and Codex

You run agents on your machine with a Claude or ChatGPT subscription, chatcode.dev keeps them fully reachable from the browser and Telegram.

Free to start Use your own AI subscription Code stays on your machine

Browser terminal

A full xterm-compatible terminal in a tab. Drag-and-drop file upload, scrollback, copy/paste – all the things you'd expect.

Persistent sessions

Each session stays alive on your server. Close your laptop, walk to a café, reopen – your agent is still there, still mid-thought.

Your VPS, your data

Code, secrets and tool state all live on the server you control. We don't store your repos and we don't keep your SSH private keys.

Bring your own AI

Works with the Claude Code, Codex, Gemini and OpenCode CLIs – signed in with your own account or key. We don't proxy inference through our own credentials.

Continuity across devices

Same session, same agent, same context – whether you opened it on desktop, mobile web, or through linked Telegram views.

Sandbox toggles

Per-session sandbox switch for Claude, Codex and Gemini. You decide whether the agent gets full access or stays in a box.

1

Sign in with your email

Magic-link auth. No password to remember, no extra account to manage.

2

Hook up a server

Easy mode: connect DigitalOcean and we'll spin up a droplet for you. If you'd rather bring your own server, install the Chatcode connection there and attach it to your account.

3

Open a session

Pick a workspace folder under ~/workspace, pick an agent (Claude, Codex, Gemini, OpenCode) and you land in a real shell. Sign into the agent once, the way you would on your laptop.

4

Keep it running

Sessions stay alive between visits. Drop files in by drag-and-drop, get Telegram updates when long jobs finish, and reattach later from anywhere.

Claude Code

anthropic · sandbox

Codex CLI

openai · sandbox

Gemini CLI

google · sandbox

OpenCode

community · BYO key

Continuity

One session, every device you carry.

The browser is the main view, but you don't always have the browser. Link Telegram and follow the same session from the Mini App and linked chats. The browser stays the main terminal view; Telegram handles continuity and notifications.

  • Same session across web and Telegram.
  • Telegram updates for session activity and long-running work.
  • Mini-app pages for picking a server and resuming a session.
  • Browser stays the full terminal; Telegram is the continuity layer.

Browser app.chatcode.dev

Chatcode connection layer

Your server + gateway Chatcode daemon on your VPS

Agent session Claude / Codex / Gemini

browser ⇄ chatcode ⇄ your server

Your code, your VPS

Files, environment variables and tool state live on the box you provisioned. We don't store your repos and we don't keep your SSH private keys.

TLS on every hop

Connections are encrypted in transit. Because Chatcode relays terminal traffic today, the service can still see it. We're upfront about that and a payload-encrypted mode is on the roadmap.

Simple setup, clear ownership

You bring the server and the AI account. We handle the browser access, session continuity, and connection layer without turning your workflow into terminal plumbing.

Honest launch scope

Some edges are still intentionally simple while we launch: no end-to-end terminal encryption yet, account-level plan limits, and a gateway safety cap for runaway sessions.

Workspace-scoped sessions

Each session is rooted under ~/workspace in a folder you choose. Sidebar groups by workspace, tabs show the relative subpath, and nothing leaks across.

Time-limited support access

If you grant us SSH for a debug session, it's an opt-in key with auto-expiry. You can revoke it in the dashboard at any time.

Is it really free?

Yes, there is a free Basic plan. Paid plans add higher limits and features such as voice transcription. The other costs are still yours: your VPS provider, your AI account or API plan, and any paid third-party services you connect.

Do I have to use DigitalOcean?

No. DigitalOcean is the easy path because we can spin a droplet up for you with one OAuth step. If you'd rather bring your own server, install Chatcode there and attach it to your account the same way.

Whose AI tokens are being used?

Yours. Each agent (Claude Code, Codex CLI, Gemini CLI, OpenCode) signs in inside the session with your own account or key. We don't proxy through our credentials and we don't bill you for inference.

What happens if I close the browser?

Nothing dramatic. The session keeps running on your VPS even after you close the page. When you come back, the terminal reconnects automatically.

Can the chatcode team see my code?

Your files live on your VPS – we don't pull them. The service acts as a trusted relay for terminal traffic today, which means an operator with access could in theory inspect what passes through. We treat that as a real trade-off rather than a marketing footnote. End-to-end terminal encryption is on the roadmap.

How many sessions can I run?

Basic and Starter currently allow 5 active sessions total and 1 server. Plus and Pro raise those account limits. Existing sessions are not killed when a plan changes, but creating new sessions is blocked while your usage is over the active plan limit.

What does “early production” mean here?

A focused product that does one thing reliably: create or connect a server, open a terminal, and keep agent work running without losing it. A few things you might expect later – end-to-end terminal encryption, multi-user workspaces, deeper enterprise controls – are deliberately not in scope yet. We'd rather ship the boring parts well than the impressive parts unevenly.

Telegram Stars can activate Starter inside Telegram. Web payments use Stripe.
VPS and AI provider costs are separate.

Want to try it?

Sign in with email, point it at a server, open a session. You can be talking to a real agent on your own VPS in about the time it takes to read this page.