AI clients and agents

Argent for Kiro CLI

Kiro CLI traffic is inspected, metered and signed by Argent while the user's own Kiro sign-in stays in place. Here is what Argent governs, how it connects and what your team sets.

AWS logo
01 / AI CLIENTS AND AGENTS

What Argent does with Kiro CLI

Every call Kiro CLI makes to a model goes through Argent first. Argent knows which agent sent it and which person owns that agent, checks it against your policy, and writes a signed record of what it decided.

  • A named agent with a human owner. Each install of Kiro CLI gets its own Argent agent identity tied to an accountable person, so no call is anonymous. Identity tethering
  • Only the models you allow. The agent can reach only the providers and models your policy names, and a request can be swapped to an approved model. Model control
  • Sensitive data handled before it leaves. Prompts and replies are scanned for personal and secret data, then redacted or blocked as your policy says. Sensitive data redaction
  • Spend priced and capped. Every request is priced and metered against budgets for the agent, its owner and the teams above them. AI spend caps
  • A signed record you can replay. Each decision becomes a hash-chained, signed audit record, and requests are grouped into sessions you can replay. Session replay
  • Tool actions checked before they run. Shell commands, file reads and writes, web fetches, MCP calls and prompt submits ask Argent first; if Argent cannot answer, the action is refused. Agent permissions
02 / AI CLIENTS AND AGENTS

How Kiro CLI connects

Kiro CLI reaches Argent in two ways.

  • TLS-inspecting forward proxy. Kiro CLI keeps its normal provider settings and sends its HTTPS traffic through the Argent forward proxy and trusts your Argent certificate; the exact settings are below. The proxy signs in with the agent's own key, so every call is attributed, then runs the same checks as the gateway. It opens only known AI hosts, and its certificate is limited to those hosts.
  • Tool hooks. Before Kiro CLI runs a tool or submits a prompt, its hook asks Argent for a decision and a data-loss scan. If Argent cannot answer, the hook refuses.

One command does the setup. argent connect kiro registers a per-tool agent under the signed-in person, keeps its key only in the OS keychain, and writes the tool's own config with a backup. --revert puts the old config back. Keyless agents explains why keys stay out of config files.

A small loopback relay holds the agent key and adds it to each proxy connection, so the key is never written into the tool's settings.

The user's own sign-in stays in place. Kiro CLI signs in to AWS with the user's token, which Argent never replaces. Turn on the tenant setting that lets Argent inspect these sign-in-bound hosts (Policy > Settings).

Proven with the real tool. Argent's team has driven Kiro CLI itself through a live Argent gateway and checked the signed records it produced.

The same steps are in the Argent console under Integrations > AI Clients, and each agent's Connect tab gives the copy-paste values for your tenant.

03 / AI CLIENTS AND AGENTS

What you configure

What your team sets in Kiro CLI. These are the settings the Argent console shows for this tool. Values in angle brackets come from your tenant.

  1. Hooks. argent login && argent connect kiro writes ~/.kiro/hooks/argent.json (version v1): PreToolUse (*), UserPromptSubmit, PreTaskExec hooks -> argent hook kiro --scope user.
  2. Route model traffic. export HTTPS_PROXY=http://<loopback relay or Argent forward proxy>; export HTTP_PROXY likewise; NO_PROXY as needed. Kiro CLI honors the proxy variables (documented for v1.8.0+). Sign-in in the browser uses the OS/browser network stack, not the CLI proxy.
  3. Tenant switch. Allow sign-in-bound vendors (Policy > Settings) on for the tenant; Kiro then runs with the unlisted-host passthrough setting off because the auxiliary hosts are catalogued as exact tunnel-only entries.
  4. Login. kiro-cli login (Builder ID, Google, GitHub, or IAM Identity Center with --license pro --identity-provider <START_URL> --region <REGION>). The user's own bearer is never replaced.
04 / AI CLIENTS AND AGENTS

Roll it out to every machine

Make it the only way Kiro CLI runs on company machines. These controls are documented by the platform each one belongs to (linked); pair them with the Argent settings above.

  • Kiro managed permissions file (IDE and CLI read the same file) (macOS). Admin deny/ask rules over agent capabilities (shell, web_fetch, mcp,...) that override a user allow. Vendor docs
  • Kiro console shared settings and MCP registry. Model access, MCP on/off, MCP Registry URL (registry-only servers), web tools, API-key generation for the profile. Vendor docs
  • Subscription via IAM Identity Center (or Okta / Entra ID) profile. Org-managed Pro/Pro+/Pro Max/Power seats billed to the company; admin assigns users/groups. Vendor docs
  • Egress allowlist from Kiro's firewall guide. Permit only the Kiro hosts you intend and force them through the Argent proxy; block personal-login paths you do not want (e.g. cognito-identity.us-east-1.amazonaws.com for social login, billing.stripe.com / checkout.stripe.com for personal-plan billing). Vendor docs

Argent ships the push kit. For managed fleets the console produces per-MDM scripts (Jamf, Kandji, Intune-style, shell and PowerShell) with your tenant certificate and proxy address built in, plus a fleet setup script and certificate bundle. Your company CA can sign the Argent certificate, so managed machines already trust it.

Want to see which AI tools people already run before you push anything? Start with Shadow AI discovery in watch mode. Watch before you enforce

05 / AI CLIENTS AND AGENTS

Check that it works

Send one request and look for the signed row. argent doctor kiro; run kiro-cli chat --no-interactive 'say OK'; Argent console live stream shows an intercept tunnel to runtime.<region>.kiro.dev with request, metering (credits) and response_inspection rows.

Every request also appears on the live stream with the agent's name and owner, and in the session view. Session replay