Skip to content
Tech News
← Back to articles

Reverse-Engineering Claude Web's MicroVM: Uncovering Anthropic's Hidden Antspace

read original get O'Reilly "Learning Go" by Jon Bodner → more articles
Why This Matters

A security-flavored teardown shows Claude Code Web runs inside AWS Firecracker microVMs, and that Anthropic shipped an unstripped Go binary with full debug symbols exposing an internal, undocumented deployment platform. It's a reminder that agent sandboxes are becoming a standard infrastructure layer, and that build hygiene matters when your runtime is handed directly to users.

Key Takeaways
Worth a Look

O'Reilly "Learning Go" by Jon Bodner — This deep dive hinges on picking apart an unstripped Go binary, and this book is a great way to build the Go fluency that makes such teardowns readable. It walks through idiomatic Go from the ground up, covering the language internals and tooling that show up in exactly this kind of investigation. A solid desk reference for anyone building or reverse-engineering Go-based infrastructure.

See O'Reilly "Learning Go" by Jon Bodner on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.

What's inside Claude Code Web: an unstripped Go binary, Anthropic's secret deployment platform, and the architecture of an AI-native PaaS

We are building ArcBox, a full-stack platform from Desktop to Platform, similar to Railway and E2B in positioning. Our core philosophy is local-cloud consistency: replacing OrbStack with a fully open-source ArcBox Desktop that provides Sandbox capabilities locally. Recently, we noticed more and more Coding Agent platforms launching web-based entry points, and remarkably, nearly all of them chose Firecracker under the hood. Claude Code is no exception. As practitioners in the same space, curiosity about its runtime environment led to some digging. What began as a casual strace -p 1 turned into a full reverse-engineering session that uncovered unreleased Anthropic infrastructure, including an entirely undocumented application hosting platform.

Everything described here was discovered through standard Linux tooling ( strace , strings , objdump , go tool objdump ) running inside a Claude Code session. No exploits, no privilege escalation, no network attacks. The binary was sitting right there, unstripped, with full debug symbols.

The first question: what exactly is this environment?

$ dmesg | grep FIRECK ACPI: RSDP 0x00000000000E0000 000024 (v02 FIRECK) ACPI: XSDT ... (v01 FIRECK FCMVXSDT ... FCAT 20240119) ACPI: FACP ... (v06 FIRECK FCVMFADT ... FCAT 20240119) ACPI: DSDT ... (v02 FIRECK FCVMDSDT ... FCAT 20240119)

The ACPI tables are signed with OEM ID FIRECK and creator ID FCAT , both hardcoded in Firecracker's source code. This is the same MicroVM technology that powers AWS Lambda and Fargate.

The specs: 4 vCPUs (Intel Xeon Cascade Lake @ 2.80GHz), 16GB RAM, 252GB disk, Linux 6.18.5. No nested virtualization since Firecracker intentionally strips vmx / svm flags from guests.

The process tree is absurdly minimal:

PID 1: /process_api --firecracker-init --addr 0.0.0.0:2024 ... └─ PID 517: /usr/local/bin/environment-manager task-run --session cse_... └─ PID 532: claude (the CLI itself)

No systemd. No sshd. No cron. No logging daemon. PID 1 is a custom binary that acts as both init and a WebSocket API gateway. The kernel command line confirms it:

... continue reading