AI Coding Tools¶
Argo Proxy v3 serves all major LLM API formats, which means it works out of the box with popular CLI tools and AI coding assistants. This guide shows how to configure each tool to use argo-proxy as its backend.
Prerequisites
All examples assume argo-proxy is running at http://localhost:44497. Replace with your actual host and port.
Your ANL username is used as the API key for all tools.
Claude Code¶
Claude Code (tested with v2.1.81) connects via the Anthropic Messages API (/v1/messages).
Important
CLAUDE_CODE_SKIP_ANTHROPIC_AUTH=1is required — it skips Anthropic's default authentication flow- Set
ANTHROPIC_BASE_URLto the proxy root (e.g.,http://localhost:44497), nothttp://localhost:44497/v1/messages— Claude Code appends the path automatically
Codex CLI (OpenAI)¶
Codex CLI (tested with v0.116.0) connects via the OpenAI Responses API (/v1/responses).
Note
Codex CLI uses the Responses API wire format by default. When using the config file approach, wire_api = "responses" makes this explicit.
Aider¶
Aider supports both OpenAI and Anthropic backends.
Tip
You can add these to your .aider.conf.yml or shell profile for persistence.
Gemini CLI¶
Gemini CLI (tested with v0.34.0) connects via the Google GenAI API (/v1beta/models/{model}:generateContent).
Important
- Set
GOOGLE_GEMINI_BASE_URLto the proxy root (e.g.,http://localhost:44497), not including any API path — Gemini CLI appends the path automatically - The
selectedType: "gemini-api-key"setting tells Gemini CLI to use the API key auth flow instead of Google OAuth - The
model.namefield insettings.jsonsets the default model, so you don't need-mevery time
Using with other proxies (e.g., OneAPI)
If your proxy expects Bearer token authentication, add this to ~/.gemini/.env:
This tells the Google GenAI SDK to send the API key as a Bearer token in the Authorization header instead of as a query parameter.
OpenCode¶
OpenCode (tested with v1.2.27) supports OpenAI-compatible endpoints.
Add a custom provider in ~/.config/opencode/opencode.json:
Kilo Code¶
Kilo Code (VS Code extension) supports Anthropic API.
Configure in Kilo Code settings:
- Base URL:
http://localhost:44497 - API Key:
your-anl-username
Generic OpenAI SDK¶
Any tool or script using the OpenAI Python SDK:
from openai import OpenAI
client = OpenAI(
base_url="http://localhost:44497/v1",
api_key="your-anl-username",
)
response = client.chat.completions.create(
model="argo:gpt-4o",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
Generic Anthropic SDK¶
Any tool or script using the Anthropic Python SDK:
import anthropic
client = anthropic.Anthropic(
base_url="http://localhost:44497",
api_key="your-anl-username",
)
message = client.messages.create(
model="argo:claude-4-sonnet",
max_tokens=1024,
messages=[{"role": "user", "content": "Hello!"}],
)
print(message.content[0].text)
Summary¶
| Tool | API Format | Base URL Env Var | Value |
|---|---|---|---|
| Claude Code | Anthropic | ANTHROPIC_BASE_URL |
http://localhost:44497 |
| Codex CLI | OpenAI Responses | OPENAI_BASE_URL |
http://localhost:44497/v1 |
| Aider (OpenAI) | OpenAI | OPENAI_API_BASE |
http://localhost:44497/v1 |
| Aider (Anthropic) | Anthropic | ANTHROPIC_BASE_URL |
http://localhost:44497 |
| Gemini CLI | Google GenAI | GOOGLE_GEMINI_BASE_URL |
http://localhost:44497 (+ ~/.gemini/.env) |
| OpenCode | OpenAI | OPENAI_BASE_URL |
http://localhost:44497/v1 |
| OpenAI SDK | OpenAI | OPENAI_BASE_URL |
http://localhost:44497/v1 |
| Anthropic SDK | Anthropic | ANTHROPIC_BASE_URL |
http://localhost:44497 |
Note
For all tools, use your ANL username as the API key. The actual authentication is handled by the ARGO backend based on your network identity.