DigitalOcean Holdings announced the public preview of DigitalOcean Managed Agents.
Managed Agents is a set of services that gives every agent its own harness runtime, governed tool access, and fast Serverless Inference in one place so that developers can easily scale agentic work without having to build and maintain infrastructure themselves. Developers can pick a harness they already use, connect tools, and have their agents do meaningful work in seconds.
Managed Agents is infrastructure for agents with pricing that reflects how they work. Harness runtimes are isolated at the hardware layer with a separate secrets management service. Auto-pause functionality stops both CPU and memory charges while a session is paused, preserving its state so work can continue when needed. Agents resume from pause in 305 ms, 46% faster than other leading offerings, while tool search is 42% more accurate than conventional methods. Active CPU billing charges developers only for CPU cycles their agents consume, with no CPU charges while agents wait for model responses or tool results. Together with DigitalOcean’s Inference Services, and full stack cloud including Managed Databases and storage, Managed Agents makes everything that an agent needs for production available in one integrated AI-Native cloud. AI Builders can experience lower latency, security-hardened infrastructure, better TCO, holistic observability, and spend less time integrating vendors and managing infrastructure.
Managed Agents is built from two vertically integrated services (Harness Runtime + Action Gateway) that share one security model and a unified billing model, with native integration to DigitalOcean's Inference Engine:
- DigitalOcean Harness Runtime combines the functionality of a lightweight microVM, built-in tools like chromium, and a coding sandbox needed by agents to do work. The product also offers rich lifecycle APIs that persist conversational history and working state across sessions, along with pause, resume, and fork semantics so that developers can control costs and adapt workflows to the nonlinear quirks of agentic work.
- DigitalOcean Action Gateway gives agents governed access to more than 16,000 tools from over 500 providers through a single managed MCP endpoint, including GitHub, Jira, Stripe, PagerDuty, and Supabase, tools for Web Search, Web Fetch and Browser Automation, and a team's own MCP servers. Credentials are brokered at execution time and never reach the model or the sandbox.
- DigitalOcean Inference Engine connects agents to Serverless Inference on DigitalOcean-hosted open-weight models such as Nemotron 3 Ultra, Kimi K3, and GLM 5.3, proprietary models like Claude Fable 5.1 and GPT 6 Astra, or to a customer's own model endpoint. Inference Router is designed to provide your workloads the best intelligence per dollar by intelligently routing requests across models based on intent, cost, latency, or quality.
Managed Agents runs widely used coding harnesses, including Claude Code, Codex CLI and OpenCode, as well as general-purpose agents such as Hermes and agents built with LangGraph, without modification. Teams can also package a custom agent as a standard Open Container Initiative (OCI) container image and turn it into a reusable template.
Because Managed Agents is integrated across DigitalOcean’s five-layer AI-Native Cloud, it has features and capabilities beyond single product vendors, including collaborative sessions, lower latency performance, and security-hardened infrastructure.
- Collaborative sessions. Sessions live in the cloud, so a developer can start a long task, close the laptop, and resume from any device or hand the live session to a teammate. Multiple users and agents can work in shared sessions, a capability unique among major cloud providers.
- Lower latency. By optimizing performance from the compute infrastructure into the software layer, in DigitalOcean testing, Harness Runtimes is able to resume from pause in 305 milliseconds, 46% faster than other leading offerings, and go end-to-end from microVM creation to agent response 31% faster.
- Fully managed harnesses. Claude Code, Codex CLI, OpenCode and Hermes run unmodified and fully managed, alongside LangGraph agents and custom OCI images, so teams keep the harness they already use, and we handle the harness lifecycle management.
- Breadth of tools. Governed access to more than 16,000 tools from over 500 providers through one MCP endpoint, with brokered credentials, centralized permissions, intelligent, model-backed tool search, and human-in-the-loop approval for sensitive actions.
- Security-hardened Infrastructure. Single sign-on, multi-factor authentication, role-based access, audit logs, cloud firewalls and DDoS protection are included on every account at no additional cost.
DigitalOcean Managed Agents is available now in public preview. Developers can create sessions with Claude Code, Codex CLI, OpenCode, Hermes, LangChain and LangGraph through the Cloud Console or the doctl CLI, and configure tool access through Action Gateway using the DigitalOcean SDK or any MCP-compatible client.
The Latest
For decades, traditional observability tools have forced IT professionals to sift through endless dashboards, turning a flood of alerts into actionable insight and driving widespread burnout. While enterprises adopted AI to eliminate this friction, most still deploy it reactively rather than proactively ... As systems become more complex and IT moves to the center of business strategy, a reactive posture is unsustainable ...
Ask an operations team what they monitor and you will hear a familiar list: latency, errors, throughput, uptime. Those signals still matter for AI, but they no longer answer the most important question. As Krishna Sai, CTO of SolarWinds, puts it: "Traditional observability tells you a system is running. AI observability tells you whether it's still reasoning soundly. Those are completely different questions" ...
AI observability serves several roles across an organization. AI engineers use it to build, evaluate, and improve AI systems. SREs use it to operate those systems reliably and efficiently in production, including managing their cost. Leaders need it to connect AI behavior and operational performance to business outcomes. The common need is a clear understanding of whether AI systems are delivering the intended result ...
Part 4 outlines the challenges enterprise face when adopting AI observability. The main challenge is that AI complexity compounds at every stage of maturity. LLM-based applications introduce new behavior, dependencies, and quality considerations, while Agentic AI adds further failure modes as systems make decisions and take actions ...
Part 3 reports on the current state of AI observability. Most experts agree: enterprises are moving faster with AI than they are with the operational discipline needed to run it safely ...
When discussing AI Observability, one of the first questions that arises: Is this just an extension of traditional observability or is this a whole new type of tool? Part 2 compares traditional observability with AI observability ...
In this extensive 14-part series that will post over the next three weeks, experts across observability and AI will provide insight and opinions on the need for AI Observability, the challenges, the benefits, the current state, and predictions for the future ...
Amid rising complexity, organizations are moving quickly toward agent-driven operations: AgenticOps, according to The Impact of Agentic AI on Network Operations, a new report from Cisco ...
AI, automation, and enterprise software give organizations an extraordinary amount of leverage. Work that once required hours can happen in minutes. Information buried across systems can be analyzed almost instantly. Complex workflows can be coordinated across teams with far less manual intervention. That leverage creates a temptation to start with the technology ...
Everyone wants to talk about models. Compute clusters. Benchmark scores that climb a fraction of a point and make headlines anyway. It's an easy conversation to have because it's measurable. But it's also increasingly beside the point ...