Documentation Index
Fetch the complete documentation index at: https://docs.runtools.ai/llms.txt
Use this file to discover all available pages before exploring further.
What is Runtools?
Every AI agent needs a place to work. Runtools gives agents private cloud sandboxes, persistent workspace storage, server-side tools, connected credentials, and workflows so they can do real tasks instead of only returning text. Use the dashboard when you want to create and operate agents visually, or use the SDK, CLI, and REST API when you want to wire Runtools into your own product.Sandboxes
Create isolated Linux or desktop environments, run commands, expose dev servers, pause idle work, and connect over SSH.
Workspaces
Persist project files, mount them into sandboxes, and give sandbox-backed agents filesystem memory across runs.
Agents
Define model, prompt, tools, execution mode, resources, and optional conversation threads. Run agents from the dashboard, CLI, SDK, or REST API.
Tool Hub
Install public tools, deploy org-private tools with
defineTool(), and let Runtools resolve OAuth or stored credentials server-side.Current Public Surface
| Surface | What you can do today |
|---|---|
| REST API | Sandboxes, workspaces, workspace files, agents, threads, workflows, SSH keys, API keys, tool execution, and secrets |
| TypeScript SDK | RunTools, rt.sandbox, rt.agent, rt.tools, rt.secrets, rt.workflows, rt.threads, rt.sshKeys, rt.devices, and workspace mounts on sandboxes |
| CLI | Auth, OAuth, project init/deploy, sandboxes with workspace mounts, agents, tools, secrets, workflows, SSH keys, usage, threads, and devices |
| Dashboard | Sandboxes, agents, tool hub, projects, workspaces, secrets, API keys, usage, and team/org management |
Quick Example
Where To Start
Quickstart
Create an API key, run the CLI, and create a sandbox.
Core Concepts
Understand sandboxes, agents, tools, workflows, projects, and credentials.
API Reference
Use the REST APIs directly.
SDK
Use the TypeScript SDK in your application.