AI clients and agents

Argent for GitHub Copilot CLI

Copilot CLI model calls go through the Argent proxy and every tool action asks Argent first. Here is what Argent governs, how it connects and what your team sets.

GitHub logo
01 / AI CLIENTS AND AGENTS

What Argent does with GitHub Copilot CLI

Every call GitHub Copilot 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 GitHub Copilot 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 GitHub Copilot CLI connects

GitHub Copilot CLI reaches Argent in two ways.

  • TLS-inspecting forward proxy. GitHub Copilot 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 GitHub Copilot 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 copilot-cli 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. GitHub Copilot CLI signs in to GitHub 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 GitHub Copilot 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 GitHub Copilot 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 copilot-cli writes ~/.copilot/hooks/argent.json with a preToolUse command hook (bash and powershell) -> argent hook copilot-cli (10 s timeout).
  2. Route model traffic. Export HTTPS_PROXY=http://<loopback relay or Argent forward proxy> (Copilot checks HTTPS_PROXY, https_proxy, HTTP_PROXY, http_proxy in that order; an https:// proxy URL is unsupported) and NODE_EXTRA_CA_CERTS=<per-tenant intercept CA PEM>. The user keeps their own GitHub login; Argent never replaces the Authorization header.
  3. Tenant switch. Allow sign-in-bound vendors (Policy > Settings) must be on for the tenant, or the proxy refuses api.*.githubcopilot.com.
04 / AI CLIENTS AND AGENTS

Roll it out to every machine

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

  • GitHub enterprise policy 'Copilot CLI'. Allow or deny Copilot CLI use for organization-provided Copilot seats. Vendor docs
  • Machine-wide proxy and CA environment (MDM script / GPO / Intune). Set HTTPS_PROXY and NODE_EXTRA_CA_CERTS for every process via launchd/systemd environment.d/Windows system env; Copilot also reads the OS trust store. Vendor docs
  • Plan-subdomain firewall rule. Corporate seats only on the corporate network (block *.individual.githubcopilot.com). 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 copilot-cli; run copilot -p 'say OK'; Argent console live stream should show intercept tunnel rows and llm request/metering rows (provider=copilot) for the agent.

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