Devin Outposts is Cognition's answer to a problem that has quietly blocked enterprise adoption of AI coding agents: the work lives on your machines, but the agent lives in someone else's cloud. With Outposts, you can now run Devin sessions on any machine you operate, from a Mac mini on your desk to a GPU cluster inside your VPC, while Devin's brain (the inference and planning loop) stays in Cognition's cloud.
The split that makes it work
Devin's agent loop, covering inference and planning, continues to run in Devin's cloud, while all command execution, file edits, and repository access happen on machines you operate. This is a clean architectural split: Cognition handles the expensive, stateful reasoning; your infrastructure handles the sensitive, environment-specific execution.
Workers only need outbound HTTPS access. No inbound ports, public IPs, or VPN tunnels are required. That means you can drop a worker inside a locked-down VPC and it will connect out to Devin's cloud without punching any holes in your firewall.
The mechanics are straightforward:
- Create a new Outpost (called a "pool") with the Devin CLI, then add a worker on your machine. Once defined, you select it as your runtime environment when starting a Devin session.
- When a user starts a session and selects a pool, the session is placed in that pool's queue. Your orchestrator claims it, spawns a machine, and runs the worker.
- When the session ends, the worker exits and your orchestrator tears the machine down.
Don't miss what's next in AI
Join 300,000+ engineers and researchers who get the signal, not the noise.
- Full access to in-depth AI research breakdowns
- Be the first to know what's trending before it hits mainstream
- Daily curated papers, repos, and industry moves