
Argent for Sourcegraph Cody
Argent sits on Cody Enterprise's model leg, so the calls your Sourcegraph instance makes are governed. Here is where Argent fits, how it connects and what your team sets.
What Argent does with Sourcegraph Cody
Argent sits between your Sourcegraph Cody service and the model. The calls Sourcegraph Cody makes to a model are sent to your Argent route instead of straight to the provider, so Argent checks and records each one.
- A named agent with a human owner. The connection uses its own Argent agent key, tied to an accountable person. Identity tethering
- Only the models you allow. The route reaches only the models your policy names. Model control
- Sensitive data handled before it leaves. Prompts and replies are scanned and redacted or blocked as your policy says. Sensitive data redaction
- Spend priced and capped, every call signed. Each request is metered against budgets and written to the signed audit ledger. AI spend caps
How Sourcegraph Cody connects
Sourcegraph Cody reaches Argent in one way.
- Gateway base URL. The model connection on the Sourcegraph Cody side points at your Argent route and uses an Argent agent key in place of the provider key. Argent adds the real provider credential from your vault on the way out.
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 Sourcegraph Cody. These are the settings the Argent console shows for this tool. Values in angle brackets come from your tenant.
- Client. VS Code extension signs in to the Enterprise instance URL (settings key cody.serverEndpoint); Cody CLI: SRC_ENDPOINT and SRC_ACCESS_TOKEN (the Sourcegraph instance, not a model API).
- Model leg (where Argent fits). Site config: modelConfiguration.providerOverrides[].serverSideConfig {type: "openaicompatible", endpoints: [{url: <Argent gateway route>}]}, with modelOverrides and defaultModels; enable cody.enabled.
Make Argent the only path
Make Argent the only path for Sourcegraph Cody. These controls are documented by the platform each one belongs to (linked); pair them with the Argent settings above.
- Sourcegraph site configuration. All Cody model traffic leaves from your Sourcegraph server to the configured provider endpoints, so developers' clients never call a model API directly. Vendor docs
Same settings everywhere it runs. The Argent fleet setup script and certificate bundle give every service, container and build runner the same proxy and certificate settings.
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. Use Cody chat; look for the llm row for the Argent key (server-side leg).
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