Credentials. Agents use your own model logins on this server, so protect the secret token and the agent login files on the machine.
Who it is forA developer whose laptop is too slow or too busy for long agent sessions and who has a spare Ubuntu 24.04 machine.
The problemAgent sessions tie up a laptop, stop when the lid closes, and leave no shared place to keep their work.
The outcomeA single Cloudroom core service on your machine that runs agents in their own room and keeps their chat history.
What you need first
- A Linux machine, such as a VPS, home server, or spare laptop, running Ubuntu 24.04 for the one-script install
- Your own logins for the agent CLIs you want to run, since agents use your own logins to call their models
- Git, and Rust 1.89 or newer if you build from source
- Optional: a Tailscale account to reach the core from other devices
Steps
- Open the [install guide](docs/setup.md) and run the one-script install on Ubuntu 24.04.
- Follow [reach it from your laptop](docs/setup.md#reach-it-from-your-other-devices) to connect over Tailscale.
- Sign in to each agent CLI you plan to use with your own login, so the agent can call its model.
- Read the [HTTP API](docs/api.md) and send a request with your secret token to create a session.
- Check the session in the saved history and confirm the agent responded.
Prompt for your agent
Using the cloudroom-core repo, install the core on <server-host> following docs/setup.md, then create one session for Claude Code using the HTTP API in docs/api.md. Expected output: the session ID and the agent's first reply. Verify that the API rejects a request sent without the secret token.
Caveat. Agents run without approval prompts, so this setup fits only a machine that belongs to you or a user you fully trust.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page