Adorbis AI
Start Free
DOCUMENTATION

Adorbis AI Docs

One key. Every model. Auto-routed. Connect any AI tool to Adorbis in under 60 seconds.

⚡ Fastest setup — run this in your terminal

npx adorbis-init

Detects your tools (Cline, Cursor, Claude Code, Aider, Continue, Roo, OpenCode, Zed) and configures them all automatically.

Quick Start

Get your free API key at ai.adorbistech.com — no credit card required. Free plan includes 1,000 credits/month.

Test your key in 30 seconds

curl https://api.adorbistech.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "adorbis/quick",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
💡 Replace YOUR_KEY with your Adorbis API key from the dashboard.

Authentication

All requests require a Bearer token in the Authorization header:

Authorization: Bearer adorbis_your_key_here

API keys start with adorbis_ and are shown once at registration. Store them securely — they cannot be retrieved again, but you can create new keys from your dashboard.

Model Departments

Instead of specifying a model, you choose a department. Adorbis routes to the best available model for that task automatically.

DepartmentBest forSpeed
adorbis/quickFast responses, chat, Q&AFastest
adorbis/coderCode generation, debugging, reviewFast
adorbis/autoSmart routing — best model for your taskVaries
adorbis/writeLong-form writing, documentationMedium
adorbis/reasonMath, logic, multi-step analysisSlower
🔁 Models behind each department are updated automatically as better options become available. You never need to change your model string.

npx adorbis-init

The fastest way to configure any AI coding tool. Works on Windows, Mac, and Linux.

npx adorbis-init

The interactive wizard will:

  1. Ask for your Adorbis API key and validate it live
  2. Show all supported tools — select one or multiple
  3. Ask which department to use (defaults to adorbis/coder)
  4. Write the correct config file for each selected tool

Supported tools: Cline, Cursor, Continue, Claude Code, Aider, Roo Code, OpenCode, Zed

VS Code Extension

Install from the VS Code Marketplace for a visual setup wizard and live credit balance in your status bar.

  1. Open VS Code → Extensions (Ctrl+Shift+X)
  2. Search Adorbis AI
  3. Click Install
  4. Open Command Palette (Ctrl+Shift+P) → Adorbis: Setup
  5. Paste your API key and click Connect
  6. Click your AI tool to auto-configure it
ext install adorbis.adorbis-ai

The extension adds a live credit balance to your VS Code status bar and auto-configures Cline, Continue, Claude Code, Aider, Roo Code, and OpenCode.

Cline

Add to your VS Code settings.json (Ctrl+Shift+P → Open User Settings JSON):

{
  "cline.apiProvider": "openai-native",
  "cline.openAiApiKey": "YOUR_ADORBIS_KEY",
  "cline.openAiBaseUrl": "https://api.adorbistech.com/v1",
  "cline.openAiModelId": "adorbis/coder"
}
OpenAI compatible

Cursor

In Cursor: Settings → Models → Add Model or use the API key settings:

Base URL:  https://api.adorbistech.com/v1
API Key:   YOUR_ADORBIS_KEY
Model:     adorbis/coder
OpenAI compatible

Claude Code

Add to ~/.claude/settings.json:

{
  "ANTHROPIC_BASE_URL": "https://api.adorbistech.com",
  "ANTHROPIC_API_KEY": "YOUR_ADORBIS_KEY"
}
Anthropic compatible

Or set environment variables:

export ANTHROPIC_BASE_URL=https://api.adorbistech.com
export ANTHROPIC_API_KEY=YOUR_ADORBIS_KEY

Aider

Add to ~/.aider.conf.yml:

openai-api-key: YOUR_ADORBIS_KEY
openai-api-base: https://api.adorbistech.com/v1
model: adorbis/coder

Or pass as flags:

aider --openai-api-key YOUR_ADORBIS_KEY \
      --openai-api-base https://api.adorbistech.com/v1 \
      --model adorbis/coder
OpenAI compatible

Continue

Add to ~/.continue/config.json under models:

{
  "models": [
    {
      "title": "Adorbis AI",
      "provider": "openai",
      "model": "adorbis/coder",
      "apiKey": "YOUR_ADORBIS_KEY",
      "apiBase": "https://api.adorbistech.com/v1"
    }
  ]
}
OpenAI compatible

MCP Servers

Adorbis AI is available as a Model Context Protocol (MCP) server — the standard used by Claude Code, Cursor, Cline, and every modern AI coding tool. Install once and your AI assistant gains access to 7 Adorbis tools automatically.

⚡ What you get after connecting

ToolWhat it does
adorbis_chatGeneral AI chat — auto-routes to best model
adorbis_codeCode generation, debugging, review
adorbis_reasonMath, logic, multi-step analysis
adorbis_writeDocumentation, articles, emails
adorbis_balanceCheck credits and connection status
adorbis_modelsList all available departments
adorbis_multi_turnMulti-turn conversation with history
💡 Once connected, just ask naturally: "Check my Adorbis balance" or "Use adorbis_code to write a Python function" — your AI tool calls the right tool automatically.

Claude Code

Two installation methods depending on your OS:

Windows (recommended)

Clone the repo and point Claude Code to the local dist file:

git clone https://github.com/adorbistech/adorbis-mcp
cd adorbis-mcp
npm install && npm run build

Then add to ~/.claude.json:

{
  "mcpServers": {
    "adorbis": {
      "command": "node",
      "args": ["C:\\path\\to\\adorbis-mcp\\dist\\index.js"],
      "env": {
        "ADORBIS_API_KEY": "your_key_here"
      }
    }
  }
}

Mac / Linux

claude mcp add adorbis -e ADORBIS_API_KEY=your_key -- npx -y @adorbistech/mcp-server

Or manually in ~/.claude.json:

{
  "mcpServers": {
    "adorbis": {
      "command": "npx",
      "args": ["-y", "@adorbistech/mcp-server"],
      "env": {
        "ADORBIS_API_KEY": "your_key_here"
      }
    }
  }
}
⚠️ Windows note: npx -y may fail on Windows. Use the node dist/index.js method above instead.

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "adorbis": {
      "command": "node",
      "args": ["/path/to/adorbis-mcp/dist/index.js"],
      "env": {
        "ADORBIS_API_KEY": "your_key_here"
      }
    }
  }
}

Cline

In VS Code, open Cline settings → MCP Servers → Add:

{
  "adorbis": {
    "command": "node",
    "args": ["/path/to/adorbis-mcp/dist/index.js"],
    "env": {
      "ADORBIS_API_KEY": "your_key_here"
    }
  }
}

MCP Tool Reference

Once connected, these tools are available inside your AI assistant:

adorbis_chat

General purpose chat. Auto-routes to the best model for your task.

Parameters:
  message      (required) — your message
  department   (optional) — adorbis/quick, adorbis/coder, adorbis/auto, adorbis/write, adorbis/reason
  system_prompt (optional) — set context for the AI
  max_tokens   (optional) — default 2048

adorbis_code

Code generation, debugging, and review. Routes to the best coding model automatically.

Parameters:
  task       (required) — coding task description
  code       (optional) — existing code to review or build on
  language   (optional) — programming language
  max_tokens (optional) — default 4096

adorbis_reason

Multi-step reasoning, math, and analysis. Routes to frontier reasoning models.

Parameters:
  problem    (required) — the problem to solve
  context    (optional) — additional data or context
  max_tokens (optional) — default 4096

adorbis_write

Long-form writing — docs, articles, emails, reports.

Parameters:
  task       (required) — writing task
  content    (optional) — source material
  tone       (optional) — professional, casual, technical, friendly
  max_tokens (optional) — default 4096

adorbis_balance

Check your API key connection status and credit balance.

No parameters required.
Example: "Check my Adorbis balance"

adorbis_models

List all available departments and their use cases.

No parameters required.
Example: "What Adorbis departments are available?"

adorbis_multi_turn

Multi-turn conversation with full message history.

Parameters:
  messages   (required) — array of {role, content} objects
  department (optional) — default adorbis/auto
  max_tokens (optional) — default 2048

WordPress Plugin

Add an AI chat assistant to any WordPress site with the [adorbis_chat] shortcode.

  1. Go to Plugins → Add New → Search for Adorbis AI
  2. Install and Activate
  3. Go to Settings → Adorbis AI
  4. Paste your API key and click Save
  5. Add [adorbis_chat] to any page or post

Shortcode parameters

[adorbis_chat
  title="Ask our AI"
  placeholder="How can I help you?"
  height="500"
  department="adorbis/quick"
  system_prompt="You are a support agent for Acme Store."
]
ParameterDefaultDescription
titleAsk AIChat header title
placeholderAsk me anything...Input placeholder
height480Chat box height in px
departmentadorbis/quickAI model department
system_prompt(from settings)Override system prompt
A floating chat bubble also auto-appears on every page when your API key is configured — no shortcode needed for the bubble.

Wix App

Install Adorbis AI from the Wix App Market to add AI chat to any Wix site.

  1. Go to Wix App Market and search Adorbis AI
  2. Click Add to Site
  3. In your Wix Dashboard → Adorbis AI
  4. Enter your API key and click Save
  5. A floating chat bubble appears on every page automatically
Customise the widget title, greeting message, accent color, and system prompt from the Dashboard settings panel.

Squarespace

Inject the Adorbis widget using a Code Block or via Settings → Advanced → Code Injection.

<script>
window.ADORBIS_CONFIG = {
  apiKey:     "YOUR_ADORBIS_KEY",
  department: "adorbis/quick",
  title:      "Ask AI",
  color:      "#1e9ad6",
  greeting:   "Hi! How can I help you today?",
  system:     "You are a helpful assistant for this website."
};
</script>
<script src="https://api.adorbistech.com/wix/widget.js"></script>

Paste this in Settings → Advanced → Code Injection → Footer.

Webflow

Add via Project Settings → Custom Code → Footer Code:

<script>
window.ADORBIS_CONFIG = {
  apiKey:     "YOUR_ADORBIS_KEY",
  department: "adorbis/quick",
  title:      "Ask AI",
  color:      "#1e9ad6",
  greeting:   "Hi! How can I help you today?",
  system:     "You are a helpful assistant for this website."
};
</script>
<script src="https://api.adorbistech.com/wix/widget.js"></script>

Chat Completions

Fully OpenAI-compatible. Drop in as a replacement for any OpenAI SDK usage.

Request

POST https://api.adorbistech.com/v1/chat/completions

{
  "model":    "adorbis/quick",
  "messages": [
    {"role": "system",    "content": "You are a helpful assistant."},
    {"role": "user",      "content": "What is Adorbis AI?"}
  ],
  "max_tokens": 1024
}

Python example

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_ADORBIS_KEY",
    base_url="https://api.adorbistech.com/v1"
)

response = client.chat.completions.create(
    model="adorbis/quick",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Node.js example

import OpenAI from "openai";

const client = new OpenAI({
  apiKey:  "YOUR_ADORBIS_KEY",
  baseURL: "https://api.adorbistech.com/v1",
});

const response = await client.chat.completions.create({
  model:    "adorbis/quick",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

All Endpoints

MethodEndpointAuthDescription
POST/v1/chat/completionsAPI KeyOpenAI-compatible chat
POST/v1/messagesAPI KeyAnthropic-compatible chat
GET/v1/auth/meJWTProfile, plan, credits
GET/v1/user/keysJWTList active API keys
GET/v1/user/usageJWTRequest history
GET/v1/pricing/plansNoneAll subscription plans
POST/v1/checkout/subscribeAPI KeyStart Stripe checkout
GET/healthNoneAPI health check

Error Codes

StatusMeaningFix
401Invalid or missing API keyCheck Authorization header format
402Insufficient creditsTop up at ai.adorbistech.com/dashboard
429Rate limit exceededSlow down requests or upgrade plan
500Server errorRetry — check status at ai.adorbistech.com
503All models unavailableRetry in 30 seconds

Plans & Pricing

PlanPriceCreditsNotes
Free$01,000 AC/moLocal models only
Starter$10/mo15,000 AC/moFull model bouquet
Pro$30/mo50,000 AC/moPriority routing
Business$100/mo200,000 AC/moEnterprise support

1 AC = $0.001 of underlying compute. Upgrade your plan →