cloudroom-core

Name: cloudroom-core
Author: davidondrej

Pending

Open-source, self-hostable Rust runtime that runs Claude Code, Codex, and Pi in the cloud.

250stars

38forks

Rust

Installation

# Add to your Claude Code skills
git clone https://github.com/davidondrej/cloudroom-core

Getting Started

Guides for using ai agents skills like cloudroom-core.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Compare with similar skills

See how cloudroom-core compares with popular alternatives.

cloudroom-core vs hermes agent

See comparison

cloudroom-core vs ecc

See comparison

README.md

Frequently Asked Questions

What is cloudroom-core?

cloudroom-core is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by davidondrej. Open-source, self-hostable Rust runtime that runs Claude Code, Codex, and Pi in the cloud. It has 250 GitHub stars.

Is cloudroom-core safe to use?

cloudroom-core's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.

How do I install cloudroom-core?

Clone the repository with "git clone https://github.com/davidondrej/cloudroom-core" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is cloudroom-core written in?

cloudroom-core is primarily written in Rust. It is open-source under davidondrej on GitHub, so you can review or fork the full source.

Are there alternatives to cloudroom-core?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh cloudroom-core against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

272,500

clicky-windows cube-pets-office

⚠️ Third-Party Software Notice

This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.

Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.

Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.

Read the Terms of Service

Cloudroom core

Website · Desktop app · Changelog · Security

Your agents get their own room in the cloud.

Cloudroom core runs coding agents on your own Linux machine and saves their chat history. It powers the cloud side of the Cloudroom app, which runs Claude Code, Codex, and Pi on your Mac or in the cloud.

Works with Codex, Claude Code, Pi, and Cursor.
Agents use your own logins to call their models.
One Rust service per machine. No Cloudroom account needed.

Don't want to host it yourself? Hosted Cloudroom is invite-only for now. Join the waitlist.

Cloudroom architecture: one cloud sandbox per agent, each running Cloudroom core and the agent.

Get started

Install on Ubuntu 24.04 with one script, on a VPS, a home server, or a spare laptop. A database on the same machine works.
Reach it from your laptop with Tailscale, and upgrade in place.
HTTP API: every endpoint, event, and error code.
Linux builds: tested binaries for each release.

Security

Agents run as a separate Linux user, with no admin rights and no sudo.
Agents can't read the core's token, database password, or history files.
Every API request needs a secret token. The API listens only on localhost unless you put it behind HTTPS.
History is saved to PostgreSQL: on the same machine, or on another one over verified TLS.
Command Guard blocks a few disastrous commands, like wiping a home folder.

Agents run without approval prompts, so give each trusted user their own machine. Report vulnerabilities privately: see SECURITY.md.

Desktop app

Download the Cloudroom app for Apple Silicon Macs (Linux alpha). Connect it to your own core with a URL and token, no account needed. The core also works without it.

Build and test

Needs Rust 1.89+, Git, and the agent CLIs you want to run.

cargo build --locked --release
cargo test --locked --all-targets

Apply the two SQL files in docs/database/ to a dedicated PostgreSQL database. The core never runs migrations itself.

More docs: storage · harnesses · session lifecycle · diagnostics · dashboard API

Contributing

Issues and pull requests are welcome. For big changes, open an issue first. This is pre-release software. Licensed under Apache 2.0.