For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.

Codex

Configure Codex AI coding tool to use agentgateway

Configure Codex, the AI coding tool by OpenAI, to route requests through your agentgateway proxy.

Before you begin

1. Install the agentgateway binary.
2. Install Codex (npm install -g @openai/codex).

Configure agentgateway

Start agentgateway with an OpenAI backend configuration. The wildcard * model name accepts any model. Codex sends the model in each request, so you do not need to pin a specific model.

1. Create a configuration file.

   cat > config.yaml << 'EOF'
   # yaml-language-server: $schema=https://agentgateway.dev/schema/config
   llm:
     models:
     - name: "*"
       provider: openAI
       params:
         apiKey: "$OPENAI_API_KEY"
   EOF

2. Start agentgateway.

   agentgateway -f config.yaml

Connect Codex to agentgateway

Point Codex at agentgateway through one of the following methods.

export OPENAI_BASE_URL="http://localhost:4000/v1"
codex

codex -c 'model_provider="proxy"' -c 'model_providers.proxy.name="OpenAI via agentgateway"' -c 'model_providers.proxy.base_url="http://localhost:4000/v1"'

[model_providers.proxy]
name = "OpenAI via agentgateway"
base_url = "http://localhost:4000/v1"

Verify the connection

1. Send a test prompt through agentgateway.

   codex "Hello"

2. Verify that the request appears in the agentgateway logs.

   Example output:

   info  request gateway=default/default listener=llm route=internal/model:* endpoint=api.openai.com:443 http.method=POST http.path=/v1/responses http.status=200 protocol=llm gen_ai.operation.name=chat gen_ai.provider.name=openai duration=1687ms

Next steps