// quickstart

Profile Your AI in 5 Minutes

Get a complete cognitive profile of any AI model. Cognum score, 10 dimensions, cognitive type.

01

Get Your API Key

Sign up at kaleiai.com and create an API key from the Dashboard → API Keys page. Your key starts with kalei_live_.

kalei_live_xxxxxxxxxxxxxxxxxxxx
02

Install the Profiler

The KALEI profiling script runs your AI agent through all 83 game environments. It supports Claude, GPT, Gemini, Groq, Mistral, and any OpenAI-compatible API.

# Clone and install
git clone https://github.com/VenelinVidenov/kalei-api
cd kalei-api && npm install
03

Run Your First Profile

Set your API keys and run. Standard depth costs 10 LMGX credits and tests ~50 rounds per environment.

# Claude
KALEI_API_KEY=kalei_live_xxx \
ANTHROPIC_API_KEY=sk-ant-xxx \
AGENT_MODEL=claude-sonnet-4-6 \
npx tsx scripts/profile-agent.ts

# OpenAI / GPT
KALEI_API_KEY=kalei_live_xxx \
OPENAI_API_KEY=sk-xxx \
AGENT_TYPE=openai \
AGENT_MODEL=gpt-4o \
npx tsx scripts/profile-agent.ts

# Any OpenAI-compatible (Groq, Mistral, xAI)
KALEI_API_KEY=kalei_live_xxx \
OPENAI_API_KEY=xxx \
OPENAI_BASE=https://api.groq.com/openai/v1 \
AGENT_TYPE=openai \
AGENT_MODEL=llama-3.3-70b-versatile \
npx tsx scripts/profile-agent.ts
04

View Your Results

Once complete, your agent's cognitive profile appears in the Dashboard → Profiles page. You'll see a Cognum score, cognitive type classification, and 10-dimension breakdown.

# Output example:
═════════════════════════════════════════════
  COGNUM SCORE: 56.61
  COGNITIVE TYPE: Temporal Strategist
═════════════════════════════════════════════

Dimension Scores:
  Cooperation              ████████████████████ 86.5
  Strategic Depth          ████████████████████ 86.3
  Temporal Reasoning       ███████████████░░░░░ 75.2
  Resource Management      ██████████████░░░░░░ 72.6
  Risk Tolerance           ███████████░░░░░░░░░ 57.5
  Information Processing   █████████░░░░░░░░░░░ 45.3
  Bias Detection           ██████░░░░░░░░░░░░░░ 33.0
  Learning Speed           ██████░░░░░░░░░░░░░░ 32.3
  Pattern Recognition      █████░░░░░░░░░░░░░░░ 28.3

Configuration Options

DEPTHstandard | deep | fullProfiling depth (10/25/50 credits)
RUNS1-10Number of runs for statistical confidence
THROTTLE_MS0-5000Delay between API calls (0 = auto)
RESUME_RUNuuidResume an incomplete run

Need help interpreting your results?

Read: Understanding Your Cognitive Profile →