
Argent for Zed
Zed's agent panel calls your Argent route, so every request is attributed, checked and signed. Here is what Argent governs, how it connects and what your team sets.
What Argent does with Zed
Every call Zed 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 Zed 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
How Zed connects
Zed reaches Argent in two ways.
- Gateway base URL. Zed 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.
- TLS-inspecting forward proxy. Zed 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.
Proven with the real tool. Argent's team has driven Zed 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.
What you configure
What your team sets in Zed. These are the settings the Argent console shows for this tool. Values in angle brackets come from your tenant.
- Gateway route. ~/.config/zed/settings.json ($XDG_CONFIG_HOME/zed/settings.json on Linux): language_models.openai_compatible.<provider-id>.api_url = https://<gateway>/<tenant-slug>/openrouter/api/v1 (the route for your tenant's OpenAI-compatible upstream; plain base URL, nothing else to set), plus available_models, e.g. {"name": "mistralai/mistral-nemo", "display_name": "mistral-nemo (via Argent)", "max_tokens": 32000, "capabilities": {"tools": true, "images": false}}. Set agent.default_model (and the thread summary model) to that provider id and model. Applies to the Zed Agent only, not External Agents.
- API key. The Argent agent key. Either enter it in Zed's Agent settings (Zed keeps it in the OS keychain) or set the environment variable <PROVIDER_ID>_API_KEY (Zed derives it from the provider id, upper-cased with dashes as underscores; a set variable means Zed never touches the keychain).
- Trust. The gateway's TLS certificate must chain to a CA in the OS trust store (MDM or GPO in an enterprise). Zed trusts only the OS store and has no per-process CA option; SSL_CERT_FILE is not honored.
Roll it out to every machine
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
Check that it works
Send one request and look for the signed row. Chat in the Agent panel; the Argent console live stream shows signed allow rows with metering for the Argent key; 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
Where to go next
Keep going. Pages that cover the same ground from another angle.
- Use case: Securing AI coding agents
- Goals: See all AI in your company, Data loss prevention, Budget and token spend, Model control and routing, Agent identity and ownership
- Capabilities: Keyless agents, Prompt injection defense, Response screening, One-click audit evidence
- Related integrations: GitHub Copilot in VS Code, GitHub Copilot in JetBrains, GitHub Copilot in Visual Studio, Cursor
- All integrations: Browse every AI client, provider, vault and identity source
Want this running on your own use cases?
Book a demo