The VMs Powering Mobile Agents (Instinct, Claude Code)
A teardown reveals Claude Code runs in Firecracker microVMs with a Rust PID 1 and MITM'd egress, while Instinct rents E2B sandboxes with git-based memory.
The author inspects the virtual machines hosting cloud agents: Claude Code runs in a Firecracker microVM with a custom Rust init (process_api) as PID 1, a 324 MB Bun harness on a read-only disk, and 443-only MITM'd SSE egress to api.anthropic.com with host-rotated OAuth tokens and no inbound access. Instinct rents E2B sandbox-as-a-service Firecracker microVMs (Ubuntu 22.04, 2 vCPU, 1.9 GB RAM) where agent memory is a git repo of Markdown committed by the agent and pushed to S3 as a single bundle, using short-lived STS credentials. Both platforms rely on Firecracker, differing mainly in fleet operator and guest boot configuration.
- Claude Code harness is a 324 MB compiled Bun binary on a read-only disk
- Claude Code egress is 443-only, MITM'd, with pinned api.anthropic.com and no inbound
- Instinct's memory is a /memory git repo of Markdown synced to S3 as bundles
- Instinct uses short-lived AWS STS credentials so leaked sandboxes self-heal
- E2B sandboxes boot a full Ubuntu with XFCE desktop in ~1.26s
- Products
- Claude CodeFirecracker
- AI models
- Claude Code
From the original article
10 min read at rohanadwankar.github.ioOne awesome product evolution is that agents (Claude Code, Instinct, Poke, etc) are moving off our local computers so that we can use them on our phones. Ultimately this is great for the customer because that means the agent companies provide us with VMs for them to run on! Here's some notes on how the major platforms work based on looking around on ws-term .
By RohanAdwankar · rohanadwankar.github.io
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.