
Argent for LiteLLM
LiteLLM can call Argent as its upstream, so every model call it routes is governed and signed. Here is what Argent governs, how it connects and what your team sets.
What Argent does with LiteLLM
Every model call an app makes with LiteLLM 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 app or service you connect uses its own Argent agent key, 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 LiteLLM connects
LiteLLM reaches Argent in two ways.
- Gateway base URL. Your app points LiteLLM at your Argent route (its base URL setting) 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 your app never holds it.
- TLS-inspecting forward proxy. Your app keeps its normal LiteLLM 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 LiteLLM 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 LiteLLM. These are the settings the Argent console shows for this tool. Values in angle brackets come from your tenant.
- As a client of Argent. In LiteLLM config set the model's api_base to the Argent route and api_key to an Argent agent key, or give the LiteLLM container the forward-proxy env (HTTPS_PROXY + CA).
- Chained. Register LiteLLM as an Argent upstream; apps then call Argent, which calls LiteLLM.
Make Argent the only path
Make Argent the only path for LiteLLM. These controls are documented by the platform each one belongs to (linked); pair them with the Argent settings above.
- Machine-wide environment variables (Windows). Sets the base URL / proxy / CA variables for every process on the machine so SDK-based apps default to Argent. Vendor docs
- Managed environment (macOS). Same variables for GUI-launched and shell processes. Vendor docs
- Service / container environment (Linux, Kubernetes, CI). Sets the variables where most production SDK code runs. Vendor docs
- Provider-side lock at OpenAI or Anthropic: only the Argent egress IP may use your org's keys. Even a stolen key or a code path that skips the base URL is rejected by the vendor. OpenAI docs, Anthropic 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. Send one chat through LiteLLM and look for a signed allow row with metering under the LiteLLM agent in the Argent console live stream.
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: Governing customer-facing AI assistants
- Use case: Controlling agent tool access: MCP and agent-to-agent
- 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: Salesforce Agentforce, ServiceNow Now Assist, OpenAI SDKs, Anthropic SDKs
- All integrations: Browse every AI client, provider, vault and identity source
Want this running on your own use cases?
Book a demo