# Agent 37

- [Build with Agent37 Cloud](https://www.agent37.com/docs/index.md): Persistent sandboxes and full Linux VMs for code, services, and agents. Run Docker, automate Android, and reach your tools over HTTPS.
- [Quickstart](https://www.agent37.com/docs/quickstart.md): Create a persistent sandbox, run a command, and reach your services over HTTPS.
- [For coding agents](https://www.agent37.com/docs/for-agents.md): Give your coding agent the documentation and a starting task.
- [Core concepts](https://www.agent37.com/docs/agents-api/concepts.md): Persistent sandboxes for code, services, and agents: instances, templates, networking, and APIs.
- [Build a custom image](https://www.agent37.com/docs/agents-api/custom-image.md): Write a Dockerfile, build the image on Agent37's infrastructure or import it from a registry, and run instances from the pinned template.
- [Move your Docker containers to Agent37](https://www.agent37.com/docs/agents-api/migrate-from-docker.md): Your Dockerfile becomes a template, each container becomes an instance that can sleep when idle, and the servers go away.
- [VM instances](https://www.agent37.com/docs/agents-api/vm-instances.md): Run Docker, Kubernetes, databases, and Android emulators on a full virtual machine.
- [Host an Android phone](https://www.agent37.com/docs/agents-api/android.md): Run an Android 14 emulator with hardware acceleration, ADB, screenshots, persistent phone storage, and a live screen in the browser.
- [Host n8n](https://www.agent37.com/docs/agents-api/n8n.md): Run n8n, the open-source workflow automation tool, on its own always-on instance, with a public URL for the editor and webhooks and the managed model ready for its AI nodes.
- [Instance lifecycle](https://www.agent37.com/docs/agents-api/instance-lifecycle.md): Understand persistence, lifecycle changes, and boot hooks.
- [Instance sizing](https://www.agent37.com/docs/agents-api/instance-sizing.md): Choose CPU, memory, disk, and an instance type.
- [Environment variables](https://www.agent37.com/docs/agents-api/instance-environment.md): Set container environment variables when you create an instance, and edit them later.
- [Auto-sleep](https://www.agent37.com/docs/agents-api/instance-auto-sleep.md): Keep an instance available while paying disk-only rates when it is idle.
- [Network access](https://www.agent37.com/docs/agents-api/instance-network.md): Cut an instance off from the internet, or let it reach only the addresses you list.
- [Backups](https://www.agent37.com/docs/agents-api/instance-backups.md): Understand backup retention and restore an instance's data.
- [Send your first agent message](https://www.agent37.com/docs/agents-api/agent-quickstart.md): Use the Agent API included in the Hermes template to start a conversation.
- [Host Claude Code](https://www.agent37.com/docs/agents-api/claude-code.md): Run Anthropic's Claude Code on its own always-on instance, signed in to your own Anthropic account.
- [Host Codex](https://www.agent37.com/docs/agents-api/codex.md): Run OpenAI's Codex on its own always-on instance, signed in to your own OpenAI account.
- [Host Grok](https://www.agent37.com/docs/agents-api/grok.md): Run xAI's Grok coding agent on its own always-on instance, on your own xAI API key.
- [Host OpenCode](https://www.agent37.com/docs/agents-api/opencode.md): Run OpenCode, SST's open-source coding agent, on its own always-on instance. Works out of the box on the managed model, no account required.
- [Host Pi](https://www.agent37.com/docs/agents-api/pi.md): Run Pi, the minimal open-source agent harness, on its own always-on instance. Works out of the box on the managed model, no account required.
- [Examples](https://www.agent37.com/docs/agents-api/examples.md): Everything you can build on the Agent37 API in one table: chat apps, a branded dashboard, your own model or Composio, custom images, webhooks, and a live agent desktop you can watch and take over, most with a forkable repo.
- [Build a chat app](https://www.agent37.com/docs/agents-api/chat-app.md): Give every user their own always-on agent. The simplest thing to build on the Agent API, and where most teams start.
- [Build a website builder](https://www.agent37.com/docs/agents-api/site-builder.md): Let your users ask an agent for a website and get a live public URL back: the agent builds and serves the site on its instance, your server publishes it.
- [Agent37 White-Label Dashboard](https://www.agent37.com/docs/agents-api/white-label.md): A white-label, multi-tenant agent dashboard built on the Agent37 API. Fork it, point it at your key, rebrand it, and ship the fastest way to put Agent37 in front of your users.
- [Build a proactive agent like Dots](https://www.agent37.com/docs/agents-api/dots.md): Give each user a named agent with its own computer that owns ongoing responsibilities, keeps its own schedule, and messages them first.
- [Build a texting assistant like Instinct](https://www.agent37.com/docs/agents-api/instinct.md): A personal assistant your users text: its own computer on Agent37, its own iMessage line, inbox, and calls through Inkbox, and reminders that text them first.
- [Build an agent team like Grok Bot](https://www.agent37.com/docs/agents-api/grok-bot.md): Give every user a team of named Bots that share one always-on computer: parallel conversations, per-Bot routines, a team chat with @mentions, and messages the Bots send first.
- [Build a personal assistant like Muse](https://www.agent37.com/docs/agents-api/muse.md): Give every user a Muse-style personal agent: its own computer, a persona and memory, daily ideas, goals it checks in on, and messages it sends first.
- [Self-host Claude Managed Agents](https://www.agent37.com/docs/agents-api/claude-managed-agents.md): Run the tools of Claude Managed Agents on an always-on Agent37 instance: Anthropic runs the agent loop, your instance runs every command and keeps every file.
- [OpenAI Agents API on Agent37](https://www.agent37.com/docs/agents-api/openai-agents.md): Connect an Agent37 instance as a self-hosted sandbox for the OpenAI Agents API, with a custom image and persistent files.
- [OpenAI Agents SDK](https://www.agent37.com/docs/agents-api/openai-agents-sdk.md): Run OpenAI Agents SDK sandbox agents in Agent37 sandboxes with a one-file client, on their own or inside Temporal workflows.
- [Cursor Self-Hosted Machines on Agent37](https://www.agent37.com/docs/agents-api/cursor.md): Run the tool calls of Cursor Cloud Agents on an always-on Agent37 instance: Cursor runs the agent, your instance runs every command and keeps the checkout.
- [LangChain Deep Agents](https://www.agent37.com/docs/agents-api/langchain.md): Run Deep Agents shell commands and file operations in Agent37 sandboxes with the langchain-agent37 Python package.
- [Browser and desktop](https://www.agent37.com/docs/agents-api/desktop.md): Browser use and computer use on Agent37: the stock agent drives a headless browser, and one cloud build gives it a full desktop you can watch live and take over.
- [Browser Use](https://www.agent37.com/docs/agents-api/browser-use.md): Run your Hermes agent's browser on Browser Use Cloud, with stealth, residential proxies, and CAPTCHA solving, by setting two environment variables.
- [Messaging channels](https://www.agent37.com/docs/agents-api/messaging.md): Connect an instance to Telegram, WhatsApp, Slack, Discord and two dozen more chat apps from your own backend, so your users message their agent from their phone.
- [Use your own model](https://www.agent37.com/docs/agents-api/byo-model.md): Run Hermes on Agent37 with your own OpenRouter key: a forkable kit with an LLM proxy you host, a revocable token per instance, per-instance spend caps, and real per-instance cost tracking.
- [Use your own Composio](https://www.agent37.com/docs/agents-api/composio.md): Run Hermes and OpenClaw on Agent37 with your own Composio API key: a forkable kit with a Composio MCP proxy you host, per-agent account isolation, OAuth connect, and per-agent tool-call metering.
- [Managed services](https://www.agent37.com/docs/agents-api/managed-services.md): Use Agent37's LLM router at OpenRouter cost with no markup, Brave Search over HTTP, and Composio and Perflo over MCP. One instance token spends workspace credit within its budget.
- [Hermes webhooks](https://www.agent37.com/docs/agents-api/hermes-webhooks.md): Give Hermes a secure public webhook URL without exposing its Agent API.
- [Text your agent on iMessage](https://www.agent37.com/docs/agents-api/imessage.md): Give each user's agent its own iMessage line, email address, and phone calls through Inkbox, with signed webhooks that wake a sleeping instance.
- [REST API reference](https://www.agent37.com/docs/agents-api/overview.md): Find endpoints, request examples, response fields, and authentication details.
- [Instances](https://www.agent37.com/docs/agents-api/instances.md): Create, inspect, and manage persistent sandboxes.
- [Create an instance](https://www.agent37.com/docs/agents-api/instances/create.md): Create a persistent sandbox from a template. All request fields are optional.
- [List instances](https://www.agent37.com/docs/agents-api/instances/list.md): List your workspace's instances, newest first.
- [Get an instance](https://www.agent37.com/docs/agents-api/instances/get.md): Read an instance's status, resources, and URLs.
- [Edit an instance](https://www.agent37.com/docs/agents-api/instances/edit.md): Change an instance's labels, metadata, environment variables, or auto-sleep settings.
- [Delete an instance](https://www.agent37.com/docs/agents-api/instances/delete.md): Permanently delete an instance and end its billing. Download anything you want to keep first.
- [Stop an instance](https://www.agent37.com/docs/agents-api/instances/stop.md): Pause an instance while keeping its files. A stopped instance bills disk only.
- [Start an instance](https://www.agent37.com/docs/agents-api/instances/start.md): Start a stopped instance or wake a sleeping one.
- [Restart an instance](https://www.agent37.com/docs/agents-api/instances/restart.md): Restart an instance using its current image and files.
- [Update an instance](https://www.agent37.com/docs/agents-api/instances/update.md): Apply a template image while preserving data in /home/node.
- [Resize an instance](https://www.agent37.com/docs/agents-api/instances/resize.md): Change an instance's CPU, memory, or disk while keeping its id and URLs.
- [Fork an instance](https://www.agent37.com/docs/agents-api/instances/fork.md): Copy an instance into an independent instance with its own id, URLs, budget, and billing.
- [List backups](https://www.agent37.com/docs/agents-api/instances/list-backups.md): List an instance's available restore points, newest first.
- [Create a backup](https://www.agent37.com/docs/agents-api/instances/create-backup.md): Back up an instance without pausing it.
- [Restore a backup](https://www.agent37.com/docs/agents-api/instances/restore.md): Replace an instance's data with a backup. Files written after that backup are lost.
- [The instance object](https://www.agent37.com/docs/agents-api/instances/object.md): Fields returned by create, get, list, edit, and fork operations.
- [Templates](https://www.agent37.com/docs/agents-api/templates.md): Name an image once, then create every instance from that name.
- [Instance and preview URLs](https://www.agent37.com/docs/agents-api/urls.md): Reach the software running inside an instance over HTTPS, at instance and preview URLs you can derive from the instance id.
- [Public ports](https://www.agent37.com/docs/agents-api/public-ports.md): Give one port of an instance a permanent, unauthenticated HTTPS URL for webhooks, embeds, and anything else that can't send an API key.
- [Custom domains](https://www.agent37.com/docs/agents-api/domains.md): Serve every URL your workspace has under your own domain, by delegating a dedicated domain's nameservers.
- [Run commands](https://www.agent37.com/docs/agents-api/exec.md): Run any shell command inside an instance from your backend, the escape hatch for anything the API does not wrap.
- [Crons](https://www.agent37.com/docs/agents-api/crons.md): Schedule a message to your agent. Each firing wakes the instance, runs the turn on its own session, and lets the instance go back to sleep.
- [SSH](https://www.agent37.com/docs/agents-api/ssh.md): Open a real shell on an instance with your own SSH keypair: ssh, scp, sftp, port forwarding, and VS Code Remote SSH, on any template image.
- [Read logs](https://www.agent37.com/docs/agents-api/logs.md): Fetch an instance's boot and runtime logs from your backend to debug a container that will not start or crashed after booting.
- [Read metrics](https://www.agent37.com/docs/agents-api/metrics.md): Fetch an instance's CPU, memory, and disk history to see whether it is sized right, spot leaks, and know before it hits a limit.
- [Managed services & budgets](https://www.agent37.com/docs/agents-api/budgets.md): Control each instance's spending on the LLM router, Brave Search, Composio, and Perflo through one budget and workspace wallet.
- [App integrations](https://www.agent37.com/docs/agents-api/integrations.md): Connect Gmail, Slack, Notion, and 250+ other apps to an instance over the Sandbox API: managed Composio, one entity per instance, OAuth handled for you.
- [Send a message](https://www.agent37.com/docs/agents-api/chat.md): Run a turn through an agent template, stream or return its result, and continue the conversation.
- [Streaming](https://www.agent37.com/docs/agents-api/streaming.md): Stream a reply as named Server-Sent Events from your instance URL, and reconnect without losing the answer.
- [Sessions](https://www.agent37.com/docs/agents-api/sessions.md): List, read, rename, and delete conversations on an instance.
- [Models](https://www.agent37.com/docs/agents-api/models.md): List the models a harness can run, and set the model and provider per turn.
- [Files](https://www.agent37.com/docs/agents-api/files.md): Browse, read, write, move, delete, and download whole folders on the instance's disk, straight from the instance URL.
- [Health & version](https://www.agent37.com/docs/agents-api/health.md): Probe whether an instance's agent is ready, and read the gateway build.
- [Sign up](https://www.agent37.com/docs/agents-api/signup.md): Create a workspace and an API key with one unauthenticated call, so an agent can onboard itself and start paying.
- [Billing](https://www.agent37.com/docs/agents-api/billing.md): Prepaid and managed in the dashboard: one workspace wallet funds compute and managed usage.
- [Members](https://www.agent37.com/docs/agents-api/members.md): Invite, list, and remove the people who share a workspace, its wallet, and its instances.
- [Errors](https://www.agent37.com/docs/agents-api/errors.md): Stable, machine-readable error codes on both planes: branch on the code, show the message.
- [Connect Hermes Desktop](https://www.agent37.com/docs/agents-api/hermes-desktop.md): Point the Hermes Desktop app at an instance over SSH.
- [Python SDK](https://www.agent37.com/docs/python-sdk.md): A one-file Python client that creates sandboxes and runs commands in them.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.