AI clients and agents

Argent for Warp

A Warp custom inference endpoint pointed at Argent puts the Warp agent's model calls under policy. Here is what Argent governs, how it connects and what your team sets.

01 / AI CLIENTS AND AGENTS

What Argent does with Warp

Every call Warp 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 Warp 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
02 / AI CLIENTS AND AGENTS

How Warp connects

Warp reaches Argent in one way.

  • Gateway base URL. Warp points its model URL at your Argent route and uses an Argent agent key in place of the provider key. Argent removes that key and adds the real provider credential from your vault on the way out, so the tool never holds it.

Proven with the real tool. Argent's team has driven Warp 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 Warp. These are the settings the Argent console shows for this tool. Values in angle brackets come from your tenant.

  1. Custom endpoint. Warp Settings > Agents > Warp Agent > Custom Inference > Custom endpoints: schema 'OpenAI Chat Completions', URL <gateway>/<tenant-slug>/openrouter/api/v1/chat/completions, API key = an Argent agent key, model IDs your tenant allows. Not used by cloud agents.
  2. Public-reachable gateway required. Warp calls the endpoint from Warp's cloud, not from your machine, so the gateway URL must be public, internet-reachable and TLS. A LAN or private gateway cannot be reached.
  3. Pick the model with /model. In the agent input type /model and search by MODEL name (the picker does not search the endpoint label). Warp hides the model-selector chip when the account shows 'Out of credits'; /model still works and custom-endpoint calls still go through.
  4. Settings file. ~/.warp/settings.toml (macOS Stable); [agents.warp_agent] is_any_ai_enabled = false turns AI off locally.
04 / AI CLIENTS AND AGENTS

Roll it out to every machine

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

  • Warp Enterprise Admin Panel. Org-enforced team policies, including forcing Warp AI off and team-managed custom endpoints that also apply to cloud agents. 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. Look for the signed llm rows for the Argent key in the Argent console live stream: a signed allow row with metering; a blocked prompt shows a signed deny row.

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