Blog

Cloud computers, instantly.

Persistent, isolated Linux machines in the cloud. Boot in under a second. Fork, share, and run anything.

Articles

  1. 01

    Where to run an agent harness in production.

    Anthropic and LangChain define what an agent harness is. This piece answers the question they don't: where does the harness actually live in production?

  2. 02

    MCP server hosting: a complete guide.

    Where do production MCP servers actually live? The four hosting patterns, what changes when MCP goes to production, and the five properties a remote MCP server host needs.

  3. 03

    Running Anthropic computer use on a remote VM.

    Computer use needs a desktop. The hard part isn't the API — it's where the desktop lives. What the workload actually needs from its host, and why most cloud primitives don't ship with a display.

  4. 04

    Self-hosted agent execution for engineering teams.

    Where does the agent actually execute? The compliance and engineering dimensions, what the substrate has to provide, and the EU sovereignty angle, honestly.

  5. 05

    The cloud dev environment: a practical guide for 2026.

    Why CDE is back in the conversation, the four shapes the category comes in this year, and what changed when AI agents joined the workload.

  6. 06

    boxd vs exe.dev: persistent SSH VMs, compared honestly.

    Two products in the same lane: persistent Linux VMs over SSH, batteries included. An honest comparison of the design choices that fall out of the shared thesis.

  7. 07

    boxd vs sprites.dev: two bets on persistent agent compute.

    Sprites and boxd agree on the architecture: persistent microVMs are the right primitive for AI agents. Where the two implementations diverge, honestly.