---
title: "Devin Outposts lets you run Devin sessions on your own machines"
url: https://daily.dev/posts/devin-outposts-lets-you-run-devin-sessions-on-your-own-machines-fmxetakxg
source_url: https://daily.dev/posts/devin-outposts-lets-you-run-devin-sessions-on-your-own-machines-fmxetakxg
type: collection
source: "Collections"
published: 2026-07-21T17:52:45.895Z
updated: 2026-07-27T04:30:21.549Z
tags: ["kubernetes", "ai-assisted-development", "devin"]
reading_time: 2
upvotes: 2
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Devin Outposts lets you run Devin sessions on your own machines

**[Collections](https://daily.dev/sources/collections)** · 2 min read · 2 upvotes · 0 comments

## Summary

Cognition has launched Devin Outposts, a new feature that allows running Devin AI coding sessions on user-controlled infrastructure — including Mac minis, GPU machines, private VMs, or Kubernetes clusters. The architecture splits responsibilities: Devin's reasoning remains cloud-based while all command execution and file edits happen locally on the user's hardware, enabling AI-assisted development without exposing internal environments to external access.

## Content

Cognition has launched Devin Outposts, a feature that splits Devin's agent loop from its execution environment. Devin's reasoning stays in Cognition's cloud, but every command, file edit, and process runs on infrastructure you control.

That could be a Mac mini in your office, a GPU box in your lab, a VM inside a private network, or a Kubernetes cluster sitting next to your internal services. One user already has Devin running on a local Mac mini specifically to handle private customer data that can't leave the building - the kind of use case that's just not possible when everything runs in a third-party data center.

## Launch partners

Several platforms launched integrations on day one:

- **Modal** - open-source integration called `modal-devin`, supporting GPU-backed sessions, custom Docker images, workspace snapshotting, and fast cold-starts. Setup is a single command: `uvx modal-devin init`, which generates an orchestrator and worker function.
- **Cloudflare** - Devin agents run in isolated sandboxes orchestrated by Workers.
- **Daytona** - supports both Linux and Windows sandboxes, with per-team isolated outposts.
- **E2B** - also confirmed as a supported environment.

## What this changes

The core idea is straightforward: Devin's brain is a cloud service, but the machine it works on is now yours. That separation matters for teams with compliance requirements, private data, or workloads that need specific hardware like GPUs.

Devin Outposts launched in alpha on July 21, 2026.

---

Tags: [#kubernetes](https://daily.dev/tags/kubernetes), [#ai-assisted-development](https://daily.dev/tags/ai-assisted-development), [#devin](https://daily.dev/tags/devin)

[View this post on daily.dev](https://daily.dev/posts/devin-outposts-lets-you-run-devin-sessions-on-your-own-machines-fmxetakxg)