For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

Managed Agents, available in public preview for all users, bring together hardware-isolated microVM sandboxes and governed tool access so you can scale agentic work in the cloud without building and maintaining any underlying infrastructure. Execute code from an existing application, run complete agents with durable sessions, or connect agents to the tools they need to act. Managed Agents includes two services that you can use independently or together, with each scaling to meet your specific needs:

DigitalOcean Harness Runtime: DigitalOcean Harness Runtime provides managed, hardware-isolated microVM sandboxes with built-in tools such as Chromium to run agents and execute arbitrary code. Rich lifecycle APIs preserve conversational history and working state across sessions, letting you pause, resume, and fork work to control costs and adapt to the nonlinear nature of agentic workflows. Scale complete agents such as Claude Code or use sandboxes independently for code execution, all through the same service.

• Execute code from any workflow. Keep your agent or application wherever it runs today and use Harness Runtime to execute code in isolated sandboxes. Run generated Python, test changes, process files, or distribute independent tasks across sandboxes in parallel.
• Run the agent itself. Launch harnesses such as Claude Code, Codex, and OpenCode inside microVM sandboxes with the filesystem, dependencies, and local tools they need to work. Harness Runtime manages the session lifecycle so you can run agents in parallel, preserve their work, and pause, resume, or branch sessions as tasks evolve.
• Control how work continues. APIs that let you pause sessions, resume with context intact, or fork from a checkpoint to explore different approaches in parallel. These controls, together with active CPU billing, help you manage costs and adapt execution to the way agents actually work.

Both scenarios use the same service and lifecycle controls, so you can scale code execution and complete agents without maintaining separate infrastructure for each. See What You Can Build with Managed Agents for example use cases.

Action Gateway: Action Gateway gives agents access to 16,000+ tools through a single managed MCP endpoint. The catalog includes DigitalOcean-maintained tools for web search, web fetch, browser automation, and DigitalOcean infrastructure management, alongside connectors for platforms such as GitHub, HubSpot, Stripe, and Snowflake. Teams can also extend the catalog with their own MCP servers and internal tools.

Together, these services provide a managed foundation for running agents, preserving their work, and governing their access to tools. You can focus on making agents more useful while DigitalOcean manages the execution, persistence, and tool infrastructure underneath.

For a walk-through of each component and the DigitalOcean services around them, see Managed Agents Architecture.

DigitalOcean Harness Runtime

Run AI coding agents in isolated DigitalOcean sandboxes with session lifecycle, permissions, and a YAML environment spec.

Action Gateway

Give agents access to tools, APIs, and connectors through a managed MCP endpoint or SDK without putting credentials in the model context.

Latest Updates

5 November 2026

• Cuttlefish, an iOS app for DigitalOcean Harness Runtime, is available in public preview on the App Store. Follow and steer sessions, approve or deny tool calls, and work with workspace files and checkpoints from your iPhone. To get started, see How to Supervise Harness Runtime Sessions from the Cuttlefish iOS App.

2 November 2026

• Persistent workspaces for DigitalOcean Harness Runtime are in public preview and are enabled per team. A persistent workspace keeps the files in /workspace after you remove the session or take a checkpoint, so a later session can start from those files. To create one and attach it to a session, see How to Use Persistent Workspaces with Harness Runtime.

26 October 2026

• DigitalOcean Harness Runtime can start a sandbox with no harness in it. Set harness: none in the environment spec, and the session boots the base image with a general-purpose toolchain and nothing running. You run commands with doctl harness-runtime exec, move files with upload and download, and reach services with port-forward. This option is available through doctl and the API. To create one, see How to Run a Sandbox on DigitalOcean Harness Runtime.

  The environment spec field that selects the adapter is now named harness. The previous name, agent, is still accepted, so existing spec files and Environment Configs work without changes. A spec can set one of the two, but not both. See the Environment Spec Reference.

For more information, see the full release notes.