Run cloud agents in your own infrastructure

2026-03-25 · Source: Cursor Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cloud Computing & & IT Infrastructure · Depth: Intermediate, quick

Summary

Cursor has released self-hosted cloud agents, allowing enterprises to run AI-powered development agents within their own network infrastructure. These agents operate in isolated virtual machines, providing a full development environment to clone repositories, set up dependencies, write and test code, and push changes for review. This offering addresses security and compliance needs for highly-regulated industries by ensuring code, secrets, and build artifacts never leave the customer's environment. Self-hosted agents maintain access to internal caches, dependencies, and network endpoints, mirroring an engineer's access. Key features include isolated remote environments, multi-model support (Composer 2 and other frontier models), plugin extensibility, and team permissions. The system uses an outbound HTTPS connection to Cursor's cloud for orchestration, while tool execution occurs on the customer's machines, with support for Kubernetes deployments via Helm charts and a fleet management API for autoscaling.

Key takeaway

For CTOs and VP of Engineering evaluating AI-driven development tools, Cursor's self-hosted cloud agents offer a critical solution for maintaining strict security and compliance while leveraging autonomous coding. You can integrate these agents directly into your existing network and build environments, offloading agent infrastructure maintenance and accelerating secure software delivery without compromising data residency requirements.

Key insights

Self-hosted AI agents enable secure, compliant code development within enterprise infrastructure.

Principles

• Security and compliance drive enterprise adoption.
• Isolated environments enhance parallelization.
• Outbound connections simplify network integration.

Method

Cursor's agent harness handles inference and planning in the cloud, sending tool calls to a dedicated worker process on the customer's machine for execution, with results returning to Cursor for subsequent inference rounds.

In practice

• Delegate end-to-end software builds to agents.
• Integrate agents with existing internal tools.
• Automate agent scaling with Kubernetes or fleet API.

Topics

• Self-hosted Cloud Agents
• Software Development Automation
• Enterprise AI Security
• Kubernetes Deployment
• AI Agent Infrastructure

Best for: CTO, VP of Engineering/Data, AI Architect, Software Engineer, DevOps Engineer, Director of AI/ML

Related on AIssential

• The Rise of Cloud Coding Agents — Cloud-based AI coding agents enable asynchronous, autonomous development workflows, enhancing scalability over traditional desktop agents.
• How to Self-Host Hermes Agent on Hostinger VPS: Step-by-Step — Hermes Agent is an open-source AI with a self-improvement loop, best self-hosted on a VPS for persistent, private, and scalable automation.
• DataRobot + Nebius: An enterprise-ready AI Factory optimized for agents — The AI Factory for Enterprises accelerates AI agent deployment and governance through specialized cloud infrastructure and comprehensive lifecycle management.
• Google Cloud Next ’26 Recap: Welcome to the era of agents — AI agents are transforming work by autonomously performing tasks at scale, supported by new platforms and infrastructure.
• Self-Hosted AI: A Complete Roadmap for Beginners — Build a private AI automation hub using Docker, Ollama, and n8n for local, cloud-independent workflows.
• Agents CLI in Agent Platform: create to production in one CLI — Agents CLI unifies Google Cloud's agent development lifecycle, enabling AI assistants to build, evaluate, and deploy production agents efficiently.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Cursor Blog.