Chat & desktop apps
Connect LibreChat
Self-hosted multi-model chat. Point it at AgentKeyRoute so every request follows your governance profile and is recorded.
Get a key with the right protection
In the console, open Connect an app (opens in a new tab) and pick this tool. AgentKeyRoute recommends a governance profile, creates the key, and shows these same steps with your key and an allowed model filled in, plus a live test.
Setup
- Install LibreChat
git clone https://github.com/danny-avila/LibreChat.git cd LibreChat cp .env.example .env docker compose up -d - Point it at the gateway
endpoints: custom: - name: "AgentKeyRoute" apiKey: "${AGENTKEYROUTE_API_KEY}" baseURL: "https://gateway.agentkeyroute.com/v1" models: default: ["gpt-4.1"] fetch: true titleConvo: true titleModel: "current_model"Replace
<your API key>with your AgentKeyRoute key.gpt-4.1is an example: use a model your key may use (GET /v1/modelslists them). - Check it works
Start a new chat in LibreChat, pick the model and say hello. The request appears in Requests (opens in a new tab) with the policy decision, the model that answered and what was redacted.
Good to know
- It uses the OpenAI-compatible API, so the base URL ends in
/v1. - If policy doesn't allow the model you chose for some data, the gateway answers with an allowed one.
X-AIGov-Modelnames it. - Refused? See Why was a request blocked?