by runtm-ai
Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.
# Add to your Claude Code skills
git clone https://github.com/runtm-ai/runtmLast scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:16:59.149Z",
"npmAuditRan": true,
"pipAuditRan": true
}runtm is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by runtm-ai. Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software. It has 282 GitHub stars.
Yes. runtm passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/runtm-ai/runtm" and add it to your Claude Code skills directory (see the Installation section above).
runtm is primarily written in Python. It is open-source under runtm-ai on GitHub, so you can review or fork the full source.
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 runtm against similar tools.
No comments yet. Be the first to share your thoughts!
Open-source sandboxes where coding agents build and deploy.
Spin up isolated environments where Claude Code, Cursor, Codex, and other agents code and ship software. With live URLs, logs, and previews.
Website · Docs · Get Started
https://github.com/user-attachments/assets/8d6d5ab8-a5c4-4a3d-8ef1-5d20b67ed3ee
# Install
uv tool install runtm
# Start a local sandbox session
runtm session start
# Your agent builds inside the sandbox...
# Deploy to a live URL
runtm session deploy
You get a live HTTPS endpoint on auto-stopping infrastructure. Machines spin down when idle and wake up on traffic.
Run AI agents in isolated local environments with OS-level sandboxing:
# Start a sandbox (auto-installs deps on first run)
runtm session start
# Start with a template
runtm session start --template web-app
# Use a different agent
runtm session start --agent codex
# List all sandboxes
runtm session list
# Reattach to a sandbox
runtm session attach sbx_abc123
# Deploy from sandbox to live URL
runtm session deploy
What you get:
┌────────────┐ ┌─────────┐ ┌─────────┐ ┌──────────┐
│ Your Agent │ ──▶ │ Sandbox │ ──▶ │ Runtm │ ──▶ │ Live URL │
└────────────┘ └─────────┘ └─────────┘ └──────────┘
The pip CLI (runtm) for local sandboxes, scaffolding, and deploys:
# Recommended
uv tool install runtm
# Alternative
pipx install runtm
# Or with pip
pip install runtm
The Go CLI (runtm-api) is a separate, lighter tool for AI coding agents driving the hosted Cloud API:
curl -fsSL https://runtm.com/install | bash
It is JSON-in / JSON-out, has stable exit codes, and ships with embedded skill files for Claude Code, Cursor, and Codex. See Agent CLI docs and the packages/agent/ source for details. The pip and Go CLIs share the same API key.
| Command | Description |
|---|---|
runtm session start |
Start a new sandbox session |
runtm session list |
List all sandboxes |
runtm session attach <id> |
Reattach to a sandbox |
runtm session stop <id> |
Stop a sandbox (preserves files) |
runtm session destroy <id> |
Destroy sandbox and delete files |
runtm session deploy |
Deploy from sandbox to live URL |
runtm init |
Initialize a new project |
runtm deploy |
Deploy to a live URL |
runtm logs <id> |
View build, deploy, and runtime logs |
runtm status <id> |
Check deployment status |
runtm destroy <id> |
Tear down a deployment |
See the CLI docs for the full reference.
Runtm can be fully self-hosted. See the self-hosting guide.
git clone https://github.com/runtm-ai/runtm.git
cd runtm
cp infra/local.env.example .env
# Install packages (includes sandbox and agents)
./scripts/dev.sh setup
# Start local services
docker compose -f infra/docker-compose.yml up -d
# Use the development CLI
runtm-dev start # Start a sandbox session
runtm-dev prompt "Build an API" # Send prompt to agent
Note: Use runtm-dev (not runtm) when self-hosting. The dev CLI includes sandbox/agents packages.
packages/
shared/ # Types, manifest schema, errors
sandbox/ # Local sandbox runtime (OS-level isolation)
agents/ # AI coding agent adapters (Claude Code, Codex, etc.)
api/ # FastAPI control plane
worker/ # Build + deploy pipeline
cli/ # Python CLI (Typer) - `runtm` (local sandbox + deploy)
agent/ # Go CLI (Cobra) - `runtm-api` (hosted Cloud API for AI agents)
templates/ # Starter projects (backend, static, fullstack)
Full docs at docs.runtm.com:
See CONTRIBUTING.md for development setup and guidelines.
| Component | License |
|---|---|
| Server (api, worker, infra) | AGPLv3 |
| CLI, Sandbox, Shared | Apache-2.0 |
| Templates | MIT |
Open an issue or join our Discord.