DigitalOcean introduces Managed Agents in public preview

X postVadim StrizheusAnnouncement

DigitalOcean has launched Managed Agents in public preview, enabling developers to run tools like Claude Code, Codex, or custom LangGraph agents in a cloud runtime that automatically pauses when idle.

Key points

  1. DigitalOcean Managed Agents is now available in public preview.
  2. The runtime environment automatically pauses when idle, stopping compute costs.
  3. Supports Claude Code, Codex, and custom LangGraph agents.
  4. Offers integration with 75+ open and proprietary models behind a governed endpoint for tools.
  5. Vadim highlights that this eliminates the need to run local hardware like a Mac mini 24/7 for agents such as OpenClaw or Hermes Agent.

Why it matters

Running persistent agents on local machines incurs hardware and energy costs even when idle. A managed cloud solution that suspends during downtime reduces operational overhead and expenses.

Analysis

Moving coding agents to managed cloud environments solves the problem of paying for idle compute when keeping machines running overnight. However, user feedback indicates that local setups still provide advantages, including direct OS-level control, UI-assisted browsing, and full custody over tools and keys.

Original post

Vadim

@VadimStrizheus · 22 September 2026

RIP to everyone who bought a Mac Mini to run OpenClaw or Hermes Agent 24/7 💀 including myself digitalocean now runs claude code and codex for you in the cloud you can close your laptop and the agent keeps working. the second it goes idle it pauses and you stop paying for t.co/eoMok6GZcg

3.1k likes271 replies4.4k bookmarks918.3k views

View on X
Selected replies (5)
  • @onlyfox83 @VadimStrizheus But also you don't own the cloud so hardware isn't a terrible idea. Also, had you not heard of a VPS before?
  • @pacioli_ai @VadimStrizheus Delegating agents to a hosting provider is the same thing as delegating custody of your crypto to a bank. #NotYourKeyNotYourAgent
  • @devmenboost @karbonx6 @VadimStrizheus Agreed, not wasted. I ran agents on a mini for a year myself. But paying for idle compute at 3am was never the smart part of that setup.
  • @Saameh0 @VadimStrizheus What about my development tools ? Do I need to install all the SDKs every time the vm boots
  • @RHLSTHRM @VadimStrizheus My Mac mini agent uses the browser and full macOS UI. I can copilot the browser with it and jump in directly when it can’t proceed without me

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:Victor Moreira

    LangChain Introduces Managed Deep Agents

    LangChain has announced Managed Deep Agents, an API-first hosted runtime in LangSmith designed for long-running AI agents. Developers can maintain agent configurations in their own repositories while LangSmith manages execution, state persistence, sandboxes, and context.

    AI & LLMs· Announcement

  • Link:Ollama

    Ollama: Platform for Open Models and Coding Agents

    Ollama provides infrastructure to run open models alongside coding agents. Beyond running models locally, it offers hosted cloud models with dedicated capacity and integrations for developer tools.

    AI & LLMs· Tool

  • Link:Hostinger

    Hostinger Claude Code VPS Hosting

    Hostinger has launched dedicated VPS hosting plans tailored for Claude Code. The servers provide persistent development environments that developers can monitor and control via Claude Code Remote on mobile or web.

    AI & LLMs· Tool

  • Link:foglamp.dev

    Foglamp: Observability Platform for AI Agents

    Foglamp is an observability tool designed for AI agents that tracks the cost, latency, and output quality of LLM calls. Setup is automated using a single prompt handed to coding agents such as Claude Code or Codex.

    AI & LLMs· Tool

  • Link:Anomaly

    OpenCode: Open-source AI coding agent

    OpenCode is an open-source AI coding agent running across terminals, IDEs, and desktop environments, offering integration with over 75 model providers.

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.