# Run cloud agents on machines you manage

Source: [Cursor](https://cursor.com/blog/self-hosted-machines)  
Feed7 permalink: https://feed7.dev/p/self-hosted-machines-1fj0tf6  
Published: 2026-09-02T12:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Cursor cloud agents can now execute tools on machines and elastic pools inside your network while Cursor retains planning and inference. This unlocks internal access and custom hardware, not full self-hosting.

## Source Summary

Cursor’s **Self-Hosted Machines** move repository access, file edits, and commands onto customer-managed workers. A worker opens outbound HTTPS to Cursor, receives tool calls, and returns results; pools can scale from a queue and serve multiple repositories.

## Practical Implication

Use this when agents need internal services, private source control, GPUs, Macs, Kubernetes, or unusual build pipelines. Linux workers now support **computer use**, and idle machines can reset, preserve a workspace, or resume from a hibernated snapshot.

## Agent-Ready Context

Cursor’s **Self-Hosted Machines** move repository access, file edits, and commands onto customer-managed workers. A worker opens outbound HTTPS to Cursor, receives tool calls, and returns results; pools can scale from a queue and serve multiple repositories.

Use this when agents need internal services, private source control, GPUs, Macs, Kubernetes, or unusual build pipelines. Linux workers now support **computer use**, and idle machines can reset, preserve a workspace, or resume from a hibernated snapshot.

Only execution moves. **Inference, planning, and the agent loop remain in Cursor’s cloud**, while tool output can include code and transcripts may be processed or stored there. Teams still need to evaluate that boundary, worker isolation, capacity controls, and recovery behavior.

## Connected Context

Feed7 judgment across 669 accumulated Signals:

This narrows “self-hosted” cloud agents to a hybrid architecture: execution can reach private infrastructure and specialized hardware, but planning, inference, and potentially sensitive tool output remain cloud-side. It strengthens the case that environment completeness is central to coding-agent usefulness while making isolation, capacity, recovery, and data-boundary review customer responsibilities.

- [What we’ve learned building cloud agents](https://feed7.dev/p/cloud-agent-lessons-06dh9iq) — Self-hosted workers directly address the earlier finding that complete development environments matter, extending cloud agents into internal services, unusual pipelines, Macs, and GPUs.
- [The Agent Behind the Curtain: Building the Oz Cloud Agent Platform — Safia Abdalla, Warp](https://feed7.dev/p/the-agent-behind-the-curtain-building-the-oz-cloud-agent-platform-safia-074nn9s) — It provides a concrete instance of Warp’s broader managed-or-self-hosted execution split, but keeps Cursor’s harness and agent loop cloud-controlled rather than making the whole platform portable.
- [Introducing organizations for Cursor Enterprise](https://feed7.dev/p/organizations-1ecywn3) — Organization-level budgets and model controls complement worker pools, but do not replace the new operational controls required for worker isolation, capacity, and recovery.

## Context Map

- Layer: tools
- Domains: coding
- Topics: cloud-agents, computer-use, enterprise

## Uncertainty

- Only execution moves. **Inference, planning, and the agent loop remain in Cursor’s cloud**, while tool output can include code and transcripts may be processed or stored there. Teams still need to evaluate that boundary, worker isolation, capacity controls, and recovery behavior.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.