Skip to main content
Accessibility
← Back to feed
Official announcementDigitalOcean Blog

Private Preview: DigitalOcean Managed Agents Runtime Services

AI agents are helping developers, teams, and businesses do more: writing and executing code, conducting research, and running dynamic workflows across systems. But that ability is often bounded by where they run. Close the laptop, and the work stops there. You can’t pick it up on

Private Preview: DigitalOcean Managed Agents Runtime Services

Unsplash (free commercial use)

AI agents are helping developers, teams, and businesses do more: writing and executing code, conducting research, and running dynamic workflows across systems. But that ability is often bounded by where they run. Close the laptop, and the work stops there. You can’t pick it up on another device, hand off to a teammate, or scale it across users. Moving agents to cloud VMs solves part of this problem; developers and companies building agent harness frameworks still have to build a high-fidelity experience that can match a local session, including agent friendly execution environments, session persistence, secure tool access, human-in-the-loop approvals, and observability.

Now available in Private Preview, DigitalOcean Managed Agents Runtime Services (M.A.R.S.) provides that infrastructure as a fully managed service. It gives developers, teams, and ISVs a powerful yet lightweight environment for operating coding agents and long-running, multi-tool agentic workflows without building and managing the underlying infrastructure themselves.

M.A.R.S. brings together two products: Harness Runtime provides the managed execution environment in which agents run, persist, and scale. Action Gateway gives those same agents governed access to the tools, APIs, and SaaS systems they need to complete real-world work.

Rather than requiring you to rebuild your agent around a proprietary framework, M.A.R.S. lets you define an environment template that packages your preferred harness, dependencies, tools, and configuration. Designed to work with Claude Code, Codex CLI, and OpenCode, as well as agents built with LangGraph or CrewAI, giving teams the freedom to choose the agent experience that best fits their needs without being locked into a single harness or framework.

[Agent sessions that outlive your laptop](#agent-sessions-that-outlive-your-laptop)[](#agent-sessions-that-outlive-your-laptop)

Harness Runtime helps agent sessions run independently of any local machine. They can start in under a second and resume from a pause in as little as 200 milliseconds while preserving their files, processes, and working state.

Developers can continue a session from another device, hand work to a teammate mid-task, or run multiple agents in parallel without multiplying the infrastructure setup. Each session runs inside an isolated Firecracker microVM, designed to separate agent-generated code from local machines and shared infrastructure.

[Govern how agents interact with the outside world](#govern-how-agents-interact-with-the-outside-world)[](#govern-how-agents-interact-with-the-outside-world)

Action Gateway gives agents governed access to services such as GitHub, Jira, Notion, Linear, and Postgres. Authentication, permissions, approvals, and audit controls are managed centrally. OAuth credentials are brokered through Secrets Manager and are exposed to neither the model nor the execution environment in which the agent runs.

[M.A.R.S. capabilities at a glance:](#m-a-r-s-capabilities-at-a-glance)[](#m-a-r-s-capabilities-at-a-glance)

  • Durable sessions: Pause and resume work without losing the session’s environment or state.
  • Isolated execution: Run agent-generated code inside dedicated Firecracker microVMs.
  • Human approvals: Define which actions agents can take autonomously and which require sign-off.
  • Native GitHub support: Allow agents to clone repositories, create branches, commit changes, and open pull requests.
  • Managed tool access: Connect agents to external systems through centrally governed authentication and policy controls.
  • Harness flexibility: Run supported coding agents, LangGraph workloads, or your own custom agent environment.

With M.A.R.S., developers retain control over the agents they build and the experiences they deliver. DigitalOcean manages the execution, persistence, isolation, scaling, and governed external access underneath them.

DigitalOcean M.A.R.S. is currently available through an invite-only Private Preview, request access here.

Anthropic pushes into physical world with new standard to help AI agents operate machines - CNBC
News summary

Anthropic pushes into physical world with new standard to help AI agents operate machines - CNBC

Anthropic News

Anthropic pushes into physical world with new standard to help AI agents operate machines CNBC

AWS Elastic Disaster Recovery introduces Recovery Plans for orchestrated application recovery
Official announcement

AWS Elastic Disaster Recovery introduces Recovery Plans for orchestrated application recovery

AWS What’s New

AWS Elastic Disaster Recovery (AWS DRS) now offers Recovery Plans, a capability that automates the sequential launch of multi-server applications during recovery and drills. Instead of launching servers one at a time and tracking dependencies manually, you define the recovery seq

Giga-Scale AI and the Ethernet Evolution: How Spectrum-X Ethernet Rewrites the Rules
Official announcement

Giga-Scale AI and the Ethernet Evolution: How Spectrum-X Ethernet Rewrites the Rules

NVIDIA Developer Blog

The massive growth of generative AI has fundamentally altered data center design. As distributed model training scales to span hundreds of thousands of GPUs,... The massive growth of generative AI has fundamentally altered data center design. As distributed model training scales

How AI Coding Agents Can Unlock Materials Simulation with NVIDIA ALCHEMI Toolkit
Official announcement

How AI Coding Agents Can Unlock Materials Simulation with NVIDIA ALCHEMI Toolkit

NVIDIA Developer Blog

Atomistic simulation requires three things: knowledge of the science, compute-efficient implementation of simulations, and accessible interfaces to the... Atomistic simulation requires three things: knowledge of the science, compute-efficient implementation of simulations, and ac

How we saved 100 terabytes of memory by optimizing 1.1.1.1’s DNS cache
Official announcement

How we saved 100 terabytes of memory by optimizing 1.1.1.1’s DNS cache

Sebastiaan Neuteboom

Big Pineapple , the platform behind 1.1.1.1 , Gateway DNS , DNS Firewall , AS112 , and several other Cloudflare DNS services, stores over 250 billion DNS cache entries at any given time. At that scale, wasting a single byte per entry costs more than 250 gigabytes of memory across

Managed PostgreSQL vs. self-hosted PostgreSQL: Key benefits and trade-offs
Official announcement

Managed PostgreSQL vs. self-hosted PostgreSQL: Key benefits and trade-offs

Lauro Ojeda

Summary This post is for technical decision makers evaluating where to run production PostgreSQL workloads. It compares two valid operating models—self-managed PostgreSQL and a managed database service—through business and operational outcomes: control, engineering capacity, resi