First Run

Guide to your first CortexPrism session.

The Setup Wizard

When you run cortex for the first time (or cortex setup), the setup wizard will guide you through:

1. Mode Selection — Choose CLI or Web interface
2. LLM Provider — Choose from 24 providers: Anthropic, OpenAI, Google, Mistral, Groq, DeepSeek, OpenRouter, xAI Grok, Together AI, AWS Bedrock, Cohere, Ollama, Cerebras, Fireworks AI, Perplexity, NVIDIA NIM, Moonshot (Kimi), Novita AI, LM Studio, LiteLLM, Hugging Face, Alibaba (Qwen), Venice AI, Kilo AI (or skip to configure later)
3. AI Personalization — Optional context about how you use AI
4. Personality Template — Choose from 8 soul templates (professional, friendly, developer, creative, analyst, teacher, minimalist, custom)
5. Channel Setup — Multi-select from 10 channel adapters: Web UI, Discord, Slack, Telegram, Microsoft Teams, Mattermost, Rocket.Chat, WhatsApp, Google Chat, and Lark. Per-channel credential prompts are shown for each selected channel.
6. Advanced Features (optional) — Configure embeddings (OpenAI/Ollama/Stub), vector store backend (SQLite/Qdrant/ChromaDB/Pinecone), Chrome Bridge (browser automation via MCP), and Voice/Speech (STT + TTS via OpenAI or ElevenLabs)
7. Telemetry — Opt in or out of anonymous usage data collection

Configuration File

After setup, your configuration is stored at ~/.cortex/config.json:

{
  "version": 1,
  "defaultProvider": "anthropic",
  "providers": {
    "anthropic": {
      "kind": "anthropic",
      "model": "claude-sonnet-4-5",
      "apiKey": "sk-ant-..."
    }
  },
  "agent": {
    "name": "Cortex",
    "maxTurns": 8,
    "streamOutput": true
  },
  "router": {
    "enabled": false,
    "strategy": "cascade",
    "confidenceThreshold": 0.7
  },
  "modelSelection": {
    "enabled": true,
    "mode": "balanced",
    "observeThreshold": 50
  },
  "update": {
    "channel": "stable",
    "checkOnStartup": true
  }
}

Data Directory

Default: ~/.cortex/data/

Override:

CORTEX_DATA_DIR=/data/cortex cortex chat

The data directory contains:

File	Contents
cortex.db	Core: sessions, jobs, policy rules, services, nodes
memory.db	5-tier memory: episodic, semantic, reflection, graph, skills
lens.db	Immutable audit log: all events, tool calls, policy checks, cost tracking
vault.db	AES-256-GCM encrypted credentials
plugins.db	Plugin registry

Your First Chat

cortex chat

On first chat, the system:

1. Starts background daemons (validator, executor, scheduler)
2. Initializes the chat session
3. Injects any relevant memory into context
4. Connects to your configured LLM provider

Type a message and the agent will respond. Try these:

• "What can you do?" — Learn about agent capabilities
• "Search the web for latest AI news" — Web search via DuckDuckGo
• "Run a Python script that calculates fibonacci" — Sandboxed code execution
• "Read the file ~/.cortex/config.json" — File reading via tool
• "Remember that I use VS Code" — Store a fact in 5-tier memory
• "Search my memory for deployment configs" — Hybrid FTS5 + vector retrieval

What Happens Behind the Scenes

Your message
  → Agent retrieves relevant memories (hybrid FTS5 + vector search)
  → Builds prompt with memory + tool context
  → Sends to LLM provider
  → LLM responds (may request tool calls)
  → Tool calls are validated by Parallax security
  → Sensitive data access checked by LLM supervisor
  → Approved tools execute (file read, web search, code run)
  → Results fed back to LLM for final response
  → Response streamed back to you
  → Session history saved to SQLite
  → Episodic memory written (async)
  → Self-reflection performed (async)
  → Tool call patterns extracted into skills (async)