DigitalOcean Managed Agents Brings Managed Cloud Infrastructure to AI Agents
DigitalOcean recently launched DigitalOcean Managed Agents in public preview, offering a managed cloud infrastructure layer for AI agents with isolated microVM runtimes, governed tool access, and serverless AI inference. By Sergio De Simone
DigitalOcean has launched DigitalOcean Managed Agents in public preview, providing managed cloud infrastructure for AI agents. This service allows developers to scale agentic work by offering isolated microVM runtimes, governed tool access, and serverless AI inference. Developers traditionally face challenges such as managing runtime environments, coordinating parallel work, maintaining spare VM capacity, and provisioning compute resources on demand when running agents on conventional VMs.
DigitalOcean Managed Agents aim to simplify these challenges by combining two integrated services: a Harness Runtime and an Action Gateway. The Harness Runtime offers persistent, isolated compute environments for agents across various harnesses, while the Action Gateway serves as the agent's interface to external tools and services, implementing several security measures and providing rate limiting, retries, backoff, and timeouts for efficient external system access.
DigitalOcean envisions this managed solution as addressing the needs of production infrastructure, providing orchestration, and supporting more tool support compared to Docker Cloud Sandboxes, which are more focused on developer workflows.
Written by urgent.news from InfoQ's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
