DigitalOcean launches Managed Agents to simplify AI agent production deployment
DigitalOcean has launched Managed Agents in public preview, a cloud service that lets developers deploy AI coding agents like Claude Code and Codex in isolated microVMs with persistent sessions, pause/resume capability, and per-second billing. The service consolidates infrastructure, inference, storage, and tool access onto a single platform and bill, addressing the complexity of running AI agents in production.
IllustrationEditorial responsibility
- No named human review is recorded for this page.
- Reports are grouped by semantic similarity and deterministic rules. Language models may assist titles, summaries, translation and cross-source analysis; the page reads the event directly, while its address stays stable when the title changes.
- Summary covers the current reports
Cross-source coverage
Reporting timeline
DigitalOcean launches agent cloud with Claude Code, Codex, and LangGraph in isolated microVMs
DigitalOcean has launched an agent cloud service, allowing users to deploy AI agent runtimes including Claude Code, Codex, OpenCode, Hermes, and LangGraph inside isolated microVMs. The service offers persistent state across sessions and the ability to pause and resume the runtime when idle, meaning users only pay for active compute time. This development positions DigitalOcean as a provider of infrastructure specifically tailored for AI agent workloads.
Read sourceDigitalOcean rolls out Managed Agent for persistent AI coding agent sessions
DigitalOcean is rolling out a new product called Managed Agent, which allows AI coding agents such as Claude Code, Codex, or LangGraph agents to run inside an isolated runtime that can pause when idle and resume with the workspace and conversation intact. The resume time is 316 milliseconds, and users do not pay while the session is paused. The service addresses the inefficiency of long-running coding agents that alternate between execution and waiting for human input, which wastes money on continuously running VMs or requires reconstructing state when killed. Managed Agent separates persistent agent state from continuously running compute.
Read sourceDigitalOcean launches Managed Agents for AI agents in public preview
DigitalOcean has announced the public preview of Managed Agents, a new cloud service designed to handle infrastructure for AI agents. The service allows users to bring their own agent—such as Claude Code, Codex, Hermes, OpenCode, or LangGraph—or even their own container, while DigitalOcean manages the underlying infrastructure. The announcement, made via a post on X, positions the product as the beginning of a new cloud era for AI agents. The service is now available in public preview, with a link provided for further information. This launch targets developers and organizations looking to deploy AI agents without managing the associated cloud infrastructure themselves.
Read sourceShow 2 older updatesHide older updates
DigitalOcean launches Managed Agents to simplify AI agent production deployment
DigitalOcean announced Managed Agents, now in public preview, aiming to simplify running AI agents in production by consolidating the entire stack onto one infrastructure and one bill. The post argues that while building a useful agent has become easy, running one in production remains a major hurdle, often requiring six different vendors and invoices. Managed Agents supports Claude Code, Codex, OpenCode, Hermes, LangGraph, or custom container images, handling microVM, inference, storage, and tool access. Key features include sessions that outlive the user's laptop, allowing multi-hour tasks to persist and be picked up by teammates, and credential brokering at execution time to keep keys away from models and sandboxes. Performance claims include 16,000+ tools behind one gateway, pause and resume in 305 milliseconds, and CPU billed per second of actual use, meaning paused agents incur zero cost. The author draws a parallel to DigitalOcean's $5 Droplet from 14 years ago, which made servers boring enough that people stopped counting them, suggesting agents will see wider adoption once running one is a single line on a bill.
Read sourceDigitalOcean launches Managed Agents to simplify AI agent production deployment
DigitalOcean has launched Managed Agents in public preview, a service designed to simplify running AI agents in production by consolidating the entire stack onto one infrastructure platform with a single bill. The post argues that while building useful agents has become easy, running them in production remains a major bottleneck, typically requiring six different vendors and invoices per agent. Managed Agents supports existing agent frameworks including Claude Code, Codex, OpenCode, Hermes, LangGraph, and custom container images, handling microVM, inference, storage, and tool access. Key features include sessions that outlive the user's laptop, allowing multi-hour tasks to persist and be resumed by teammates, and credential brokering at execution time to keep API keys away from models and sandboxes. Performance claims include 16,000+ tools behind one gateway, pause and resume in 305 milliseconds, and CPU billed per second of actual use, meaning paused agents incur zero cost. The author draws a parallel to DigitalOcean's $5 Droplet from 14 years ago, which made servers boring enough that people stopped counting them, suggesting agents will see widespread adoption once running one is a single line on a bill.