Your AI coding agents,
on a server you own.
chatcode.dev is a browser terminal that opens persistent AI coding sessions on your own VPS. Bring the Claude Code, Codex or Gemini account you already use. Pick up where you left off – from a laptop, a phone, or Telegram-linked views – without losing context or rebuilding your setup.
A small piece of glue between
your browser and your server.
You bring a server. We give you a clean way to run AI agents inside it – visible from anywhere, with persistent session continuity and a simpler browser workflow than raw SSH alone.
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.
From signup to a live session in a few minutes.
Four steps and one of them is “wait roughly thirty seconds for your server to come online.”
Sign in with your email
Magic-link auth. No password to remember, no extra account to manage.
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.
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.
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.
The CLIs you already use, ready on your server.
Claude Code and Codex are the fastest path on a fresh setup. Gemini and OpenCode can be added from the app when you need them.
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.
What runs where, in plain words.
We'd rather be specific about the trade-offs than wave hands. The short version is below.
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 MVP scope
Some edges are still intentionally simple while we're in MVP: no end-to-end terminal encryption yet, and high session counts are still capped.
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.
Reasonable questions, short answers.
Is it really free?
chatcode.dev itself is free to start using – there's no pricing page yet, and no credit card to sign up. The cost you do pay is for your own VPS (DigitalOcean droplet or any Linux box you already have) and for whichever AI account or API plan you bring along.
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?
On the free plan, it's capped at
10 concurrent sessions per VPS. That's plenty
for most workflows; if you bump into it, get in touch.
What does “MVP” actually mean here?
A small product that does one thing reliably. The first release focuses on “create a server, open a terminal, do work without losing it.” A few things you might expect from a v1.0 – end-to-end terminal encryption, paid plans, multi-user workspaces – are deliberately not in scope yet. We'd rather ship the boring parts well than the impressive parts unevenly.
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.