Credential containment for every workflow

Integrations

See how teams use Cordon to contain credentials across AI agents, developer environments, CI/CD pipelines, and applications.

AI Agentic Development Tools
Terminal

# Set up cordon for Claude Code

$ cordon setup claude-code

 

Setting up cordon for Claude Code

 

Checking TLS certificates

CA certificate: ~/.config/cordon/certs/ca-cert.pem

 

Detecting secret providers

1Password CLI added to config

 

Configuring Claude Code settings

Target: .claude/settings.local.json

HTTPS_PROXY = http://127.0.0.1:6790

NODE_EXTRA_CA_CERTS = ~/.config/cordon/certs/ca-cert.pem

Wrote .claude/settings.local.json

 

Setup complete

 

NEXT STEPS

Start the proxy cordon start

Verify status cordon status

Claude Code

Claude Code

Anthropic's AI coding agent

Start using Cordon, Codezero's Credential Containment Layer, with Claude Code using one simple command.

Claude Code calls external services through MCP tools, command-line tools, and direct API calls. Today, that means credentials end up everywhere — environment variables, .env files, MCP server configs, shell history, clipboard buffers. Even credentials that aren't actively in use sit on the developer's machine, accessible to any process, any agent, or any prompt injection that knows where to look.

Cordon eliminates the problem at its root. Credentials are never written to disk, never loaded into memory, and never passed through environment variables. Instead, Cordon intercepts outbound requests and injects credentials just-in-time — in transit, outside the agent's reach. Claude Code makes the call; Cordon handles the authentication. The credentials simply aren't there to steal.

Codex

Codex

OpenAI's AI coding agent

Same credential containment, same one-command setup. Codex gets the same protection as any other agent.

Codex reads and writes code, runs shell commands, and calls APIs on your behalf. Cordon ensures every outbound credentialed request is mediated — no secrets in environment variables, no tokens on disk.

Terminal

# Set up cordon for Codex

$ cordon setup codex

 

Setting up cordon for Codex

 

Checking TLS certificates

Using existing CA certificate

 

Detecting secret providers

1Password CLI added to config

 

Configuring Codex settings

Target: .codex/.env

HTTPS_PROXY = http://127.0.0.1:6790

SSL_CERT_FILE = ~/.config/cordon/certs/combined-ca.pem

Wrote .codex/.env

 

Setup complete

 

NEXT STEPS

Start the proxy cordon start

Verify status cordon status

Terminal

# Set up cordon for Hermes

$ cordon setup hermes

 

Setting up cordon for Hermes Agent

 

Checking TLS certificates

CA certificate: ~/.config/cordon/user/certs/ca-cert.pem

 

Detecting secret providers

1Password CLI added to config

 

Configuring Hermes settings

Target: ~/.hermes/.env

HTTPS_PROXY = http://127.0.0.1:6790

SSL_CERT_FILE = ~/.config/cordon/user/certs/combined-ca.pem

Wrote ~/.hermes/.env

 

Setup complete

 

NEXT STEPS

Start the proxy cordon start

Verify status cordon status

Hermes

Hermes

Nous Research's autonomous AI agent

40+ built-in tools, self-improving behavior, and the same credential containment from Cordon.

Hermes Agent calls web APIs, runs commands, and manages files autonomously. With Cordon, every outbound request is credential-contained — the agent works freely while secrets stay out of reach.

Get started in minutes

One command. No code changes. Credentials stay out of reach.