rye.ai
Menu
supervision docsEnvironmentv

Rye supervision workbench

Environment

Understand the local environment surface that AI coding agents inherit and how Rye supervises it.

Start free trialView pricing

Agent environment

Coding agents inherit the developer's shell environment. That can include API keys, cloud credentials, local config paths, SSH agent access, package manager settings, and proxy variables.

Rye supervision is most reliable when the agent process is launched through Rye, because the process sees proxy and trust settings at startup.

Recommended launch pattern

Use:

exec:bash
rye wrap claude
exec:bash
rye wrap codex

For repeated use, install shims:

exec:bash
rye app wrap claude
exec:bash
rye app wrap codex

Keep scope explicit

Rye scopes proxy and CA environment variables to wrapped sessions. The installer configures PATH for binaries and shims, without persisting global HTTP proxy variables. rye doctor --fix also leaves global proxy variables unset unless you explicitly add --set-global-http-proxy.

The wrapper configures routing through environment variables. It does not impose an OS sandbox or prevent a child from changing its environment or using a direct network connection.

Files and secrets

Agents can read local files when the runtime permits it. Policy should account for files such as:

  • .env
  • cloud credential files
  • SSH config
  • package manager tokens
  • Terraform state
  • customer exports

The goal is not only to prevent obvious key leakage. It is to reduce accidental movement of sensitive context into model requests.