DigitalOcean Holdings, Inc. has announced the public preview of DigitalOcean Managed Agents, a set of services designed to help developers build and scale AI agents without managing the underlying infrastructure. The offering provides each agent with an isolated harness runtime, governed tool access and Serverless Inference through an integrated AI-Native Cloud environment. Managed Agents addresses requirements created by increasingly complex agentic workloads, including security, persistence and rapid responsiveness, by providing hardware-isolated environments, externally brokered credentials and persistent sessions that can pause, resume and fork. Following its private preview, Managed Agents is now publicly available, with OpenHands, Qencode and Amplitude already building on the platform.
Also Read: Sumo Logic Enhances Data Pipelines for Telemetry Cost and Data Management
“EC2 was the front door to the first generation cloud. Customers rented a virtual machine and assembled everything else around it. The next generation cloud is AI-native, and the agent is the front door. Agents need an integrated platform with inference and tokens to think, computers to execute, and data and applications for context, persistence, and user interaction. That integrated platform is DigitalOcean’s AI-Native Cloud.” The platform combines DigitalOcean Harness Runtime with Action Gateway and Inference Engine, providing lifecycle management, access to more than 16,000 tools from over 500 providers, and serverless model inference. Developers can use coding harnesses including Claude Code, Codex CLI and OpenCode, as well as general-purpose agents and custom OCI container-based agents.