Free
$0
- 10 new sessions every week, including automations
- 5 hours on a Bivy computer, once
- Live previews, feedback and share links
- All integrations included
- No credit card
The open-source workspace for coding agents
Bivy runs Claude Code, Codex, Pi or any agent you bring, on the subscriptions you already pay for. Run it on your laptop, your server or a cloud computer, follow it from your phone, and try the app it built right in the chat.
10 free sessions a week · No credit card · Open source
Works with any coding agent
01 Any agent

02 Any machine
Every session runs on a machine you pick. Start on your laptop, then move the session to the cloud when you close the lid.
Agents use your repo, local services, databases and tools as they are. Nothing to rebuild in a sandbox.
It has its own disk, so tools and logins you set up are there next time. It sleeps when the work stops and wakes when you send.
A fresh machine for one task, so parallel work never shares a checkout. Delete the session and the runner goes with it.
Watch the session live, answer questions, approve tool calls, or stop it. Agents can ping you and wait for your answer.
Every machine dials out. Prompts, transcripts, diffs and files are end-to-end encrypted between it and your devices.
When an agent needs a token, it asks in the chat. You paste it once. The agent gets a reference, never the value.
Bivy is MIT licensed. Run the whole thing on your own server, cloud computers included.
03 Live previews
Bivy finds the dev server your agent starts and opens it next to the chat: web apps, terminals, even desktop apps. Here’s one change to a small demo app.

01 · Preview
Open it beside the chat. Here, packed items crowd the top of the list.

02 · Feedback
Your drawing and note go to the agent with the page context. No screenshots to paste.

03 · Review
The agent’s reply comes with the app as it looks now. Flip to Before, open it live, or share it.
04 Automations
Send a GitHub issue, a failed CI run, a Linear ticket, a Slack message, a schedule or any webhook to Bivy. An agent picks it up on your machine and posts back a preview link or a pull request.
01 / The trigger
“Build a weekend packing checklist.”
Here, a Basecamp to-do fires a webhook.
02 / On your machine
It writes the code and runs your tests in your repo, with your tools.
03 / Back to you
The preview link lands in the to-do. Open it, try the app, and reply in the same session.
“Separate packed items from what is left.”
Start work from
$0
$15/mo
$0
Your own computers are unlimited: you bring the machine, and sessions you start on it never count. A Bivy computer sleeps when the work stops, and sleeping is free. Extra hours are $0.10, up to a ceiling you set. You bring your own agent subscription or API key.
A place to run the coding agents you already use and follow them from anywhere: chat, terminal, live app previews, automations and review, from your desk, browser or phone. It’s not another coding agent. Work runs on your own computers, on your Bivy cloud computer, or on a runner made for one task.
Your own machine has to stay awake while it runs the work. Use an always-on server if you want that work to continue while your laptop is closed. A Bivy computer sleeps when the work stops and wakes when you come back.
20 agents are supported, including Claude Code, Codex, Pi, OpenCode, Gemini CLI, Grok, Kimi Code, Cursor, GitHub Copilot, Amp, Goose and Aider. For any other CLI or ACP agent, ask your agent to add it: it writes a small adapter and tests it, with no change to Bivy. Capabilities such as resume, model choice and approvals vary by agent.
All agents and what each supports ↗A fork or move takes the code and conversation context with it. How much history transfers depends on the agents involved, so check the new session before retiring the original. Switching doesn’t reset the first provider’s limit, and automatic retry needs a reset time from the provider.
How session handoffs work ↗An automation rule for the source (GitHub, Linear, Slack, a schedule or a signed webhook). To post a preview link back to a tool like Basecamp, the agent needs credentials for that tool.
Webhook recipes ↗Bivy Cloud runs the app and relay for you, plus a cloud computer and runners that sleep when you stop. Self-hosting runs the same MIT-licensed software on your server for $0, cloud computers included if you connect a Fly.io account. You supply model access either way.
Self-host guide ↗Interactive prompts, transcripts, diffs, files, and model keys are end-to-end encrypted between your machine and paired devices. Your model provider receives what your agent sends; Slack commands and generic webhook instructions reach the routing service as plaintext. Anyone with a preview share link can use that app until the link expires or you revoke it. A Bivy cloud computer runs in our Fly.io account: we don’t look at it, but we and Fly.io can technically reach it. If that matters, use your own machine.
Security boundaries ↗Not universally. Some agents have native sandboxing or structured approvals; others run largely as you. Choose permissions and isolation appropriate to the agent and task.
Agent security model ↗