Getting Started

Quickstart

Get your first TARX inference response in under 2 minutes.

1. Install the daemon

curl -fsSL tarx.com/install | sh

This installs the 2.9MB tarxd daemon and registers it as a background service. The 4.7GB model downloads automatically. Menu bar icon shows download progress.

2. Verify the daemon is running

curl http://localhost:11435/health
# → {"status":"ok","model":"tarx-qwen2.5-7b"}

3. First request — Python

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:11435/v1",
    api_key="none"
)

response = client.chat.completions.create(
    model="tarx-qwen2.5-7b",
    messages=[{"role": "user", "content": "Hello"}]
)

print(response.choices[0].message.content)

4. First request — curl

curl http://localhost:11435/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tarx-qwen2.5-7b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

5. Migrate from OpenAI

Already using OpenAI? One line.

# Before
client = OpenAI(api_key="sk-...")

# After
client = OpenAI(base_url="http://localhost:11435/v1", api_key="none")

All endpoints, parameters, and response shapes are identical to OpenAI's API.