Claude Code arrives in AWS GovCloud, bringing AI coding to ITAR-regulated workloads
AWS ML Blog · rss · 2026-10-06
AWS announced that Claude Opus 5.5 and Claude Sonnet 5.5 are now available in AWS GovCloud (US) regions, enabling Claude Code workflows for regulated workloads including ITAR. Claude Sonnet 5 holds FedRAMP Class D certification and DoD IL4/IL5 authorization.
Key points:
- Two endpoint surfaces: bedrock-runtime (SDK-based, supports Guardrails, Knowledge Bases, invocation logging — recommended for audit trails) and bedrock-mantle (native Anthropic Messages API with server-side tools, background inference, Projects).
- Customer content is not stored, logged, or used for training, built on the Zero Operator Access (ZOA) architecture.
- Setup options: interactive wizard (/login → Amazon Bedrock), environment variables (CLAUDECODEUSEBEDROCK=1, AWSREGION='us-gov-west-1', ANTHROPICMODEL), or the Mantle endpoint (CLAUDECODEUSEMANTLE=1).
- The guide includes IAM permission lists, install commands, and how to pin model versions for teams via ANTHROPICDEFAULTOPUSMODEL and similar variables.
More from coding & agent
- Gradio says training your own models via a single ml-intern prompt is huge alpha — Gradio · 2026-10-06
- Most performance wins are under 5 lines of code — a 20% zstd fix case — DanielLockyer · 2026-10-06
- Developer laments that Claude Code and Codex do everything, leaving him out of the loop — zsakib_ · 2026-10-06
- Building agent skills from a structured wiki distilled from past experience — rseroter · 2026-10-06
- Using EvoX to draft bug reports: AI quietly turns "not shown" into "user skipped" — yawning42 · 2026-10-06
- Chunkr: open-source Rust chunking lib claims ~20x speedup over LangChain with full benchmarks — Ok_Cartographer5609 · 2026-10-06