Overview

The cogitator wizard command provides an interactive TUI to configure a personal AI assistant. It generates a cogitator.yml config and .env file with all required secrets.

Quick Start

npx @cogitator-ai/cli wizard

The wizard walks you through:

LLM provider and model — Google, OpenAI, Anthropic, or Ollama
Channels — Telegram, Discord, Slack (with token prompts)
Capabilities — web search, file system access, scheduler, RAG
Memory — adapter, knowledge graph, auto-extraction
Personality — custom system prompt for the assistant

After setup, start the assistant:

cogitator up

Editing an Existing Config

Re-run the wizard with --edit to modify an existing cogitator.yml:

cogitator wizard --edit

This loads the current config and lets you change individual sections.

Generated Files

cogitator.yml

name: jarvis
personality: |
  You are Jarvis, a personal AI assistant.

llm:
  provider: google
  model: google/gemini-2.5-flash

channels:
  telegram:
    ownerIds: ["123456789"]

capabilities:
  webSearch: true
  scheduler: true

memory:
  adapter: sqlite
  path: ~/.cogitator/memory.db
  knowledgeGraph: true

.env

GOOGLE_API_KEY=your-api-key
TG_TOKEN=your-telegram-bot-token

Programmatic Equivalent

Instead of the wizard, you can use RuntimeBuilder directly:

import { RuntimeBuilder } from '@cogitator-ai/channels';

const builder = new RuntimeBuilder({
  name: 'jarvis',
  personality: 'You are Jarvis, a personal AI assistant.',
  llm: { provider: 'google', model: 'google/gemini-2.5-flash' },
  channels: { telegram: { ownerIds: ['123456789'] } },
  capabilities: { webSearch: true, scheduler: true },
  memory: { adapter: 'sqlite', path: '~/.cogitator/memory.db', knowledgeGraph: true },
}, process.env);

const runtime = await builder.build();
await runtime.gateway.start();

Config Reference

Field	Type	Default	Description
`name`	`string`	required	Assistant name
`personality`	`string`	required	System prompt / personality
`llm.provider`	`google \| openai \| anthropic \| ollama`	required	LLM provider
`llm.model`	`string`	required	Model identifier (e.g. `google/gemini-2.5-flash`)
`channels`	`object`	`{}`	Channel configs (telegram, discord, slack)
`capabilities`	`object`	`{}`	Enabled capabilities
`memory.adapter`	`sqlite \| postgres`	`sqlite`	Memory storage backend
`memory.knowledgeGraph`	`boolean`	`true`	Enable knowledge graph
`memory.autoExtract`	`boolean`	`true`	Auto-extract entities from conversations
`stream.flushInterval`	`number`	`600`	Stream flush interval (ms)
`stream.minChunkSize`	`number`	`30`	Minimum chunk size before flushing
`rateLimit.maxPerMinute`	`number`	`30`	Per-user rate limit

Wizard Setup