Claude Code cloud environments: save deps, network, and API keys for the next session
SummaryOn Pro, Max, Ultra (and Team / Enterprise premium or Chat+Code seats), Claude figures out dependencies, network access, and API keys for a cloud session, then saves the environment. Network secrets stay outside the VM — Anthropic's agent proxy attaches them after the request leaves. Paid tiers only; not tested by MODEL.
· MODEL Editors · 1 min read
Some links may be affiliate links. Disclosure
Claude Code cloud sessions can now keep a saved environment so the next run starts closer to ready. @ClaudeDevs (Nov 6, 2026): Claude figures out what dependencies, network access, and API keys a repo needs, then saves that environment for next time. API keys are stored so Claude never sees them.
What it does. Each cloud session runs in a cloud environment (Desktop, mobile, claude.ai/code, claude --cloud, scheduled tasks, Claude Tag). You can set network access, environment variables, a setup script, and network secrets. When setup finishes fast enough, Anthropic caches the filesystem snapshot so later sessions skip reinstalling deps. Network secrets are different from env vars: Anthropic's agent proxy attaches the key to requests for the hosts you list after the request leaves the session VM, so the key stays outside the VM.
Who it's for: Pro, Max, and Ultra users running cloud sessions — docs also list Team and Enterprise users with premium seats or Chat + Claude Code seats. Useful if you keep re-teaching Claude the same toolchain and API hosts for a repo.
Caveats. Cloud sessions are paid-tier (not Free). The "Claude never sees the key" claim is Anthropic's architecture description — MODEL has not independently audited it. Default Trusted network is allowlisted domains only; other hosts need Full or Custom. MODEL has not tested this flow.
Disclosure: Not sponsored. No affiliate links. Not tested by MODEL.
MODEL Editors
Sources
- Configure cloud environments
Anthropic / Claude Code docs
- Claude Code on the web
Anthropic / Claude Code docs
- Announcement: easier cloud session setup
@ClaudeDevs on X
Keep reading
RESEARCH
Claude agents dream offline — Anthropic on the components of agent memory
Nov 6, 2026 Anthropic Engineering (Lance Martin): agent memory as notes + offline dreaming. Pokémon Red: Sonnet 3.7 wrote 413 files across 225 folders (1 badge); Fable 5 wrote 9 files + global.md (4 badges). Dreaming corrected a wrong Mt. Moon PokéCenter note after Claude walked a ledge 3×.
· MODEL Editors
SECURITY
Claude Code leaked signed-in emails into User-Agent — Anthropic shipped a narrow privacy mod
Claude Code put the signed-in account email into model context; the model sometimes invented HTTP User-Agent headers with that address on outbound web/shell calls. Anthropic confirmed on HN and shipped built-in cc-plugin-privacy from 2.1.317+ (default on). Mod is a courtesy, not a boundary — WebFetch/WebSearch/MCP unchecked.
· MODEL Editors
AI NEWS
METR: Anthropic AI R&D sped up ~1.9× — mostly from AI assistance, not faster compute scaling
Independent high-access eval (Aug–Oct 2026): AECI growth since Oct 2025 estimated at 1.9× the prior rate (95% CI 1.5–2.8×). Acceleration not from faster training-compute scaling; majority likely AI-assisted R&D. Catch: Anthropic redacted most of the most-informative evidence.
· MODEL Editors
FREE · EVERY WEEK
The top AI tools this week, tested.
Every week MODEL's editors pick the AI tools worth your time, try them hands-on, and tell you what's good, what's not, and who it's for. Free, in your inbox.
Free. Unsubscribe anytime. Our picks are editorial and can't be bought.