AI Starter Package
Based on real production setup

OpenClaw AI Brain Setup Guide

This is exactly how we configure the AI brain for our managed agent customers. 7 layers, 250+ agents, 7-tier memory, scheduled workflows — all pre-configured.

For managed agent customers: We set all of this up for you. You just fill the onboarding form and we deliver a working system within 48 hours. This guide is for those who want to understand what's inside or set it up themselves.

7-Layer Architecture

The AI brain is built in layers. Each layer handles a specific concern, and they stack to create a complete operating system for your AI agents.

1

Security Layer

NVIDIA NeMo Guardrails

Filters harmful content, enforces policies, protects your data

2

Agent Core

OpenClaw

Orchestrates your agents, routes tasks, manages execution

3

Token Economy

Cost tracking

Monitors token usage, tracks cost per task, optimizes spending

4

Skill System

1,730+ skills

Pre-loaded capabilities organized by domain

5

Agent Pool

250+ specialists

Each agent handles a specific type of work

6

Workflow Engine

Scheduled tasks

Morning briefings, health checks, daily syncs — automated

7

Memory Architecture

7 tiers

Session, working, long-term, agent, knowledge base, and daily notes

12-Agent Army

Each agent specializes in one area. They run independently but share memory and coordinate through the orchestrator. Costs shown are approximate API token costs per task.

AgentPurposeEst. Cost/Task
AuditorQuality gate — reviews work, promotes knowledge, proposes SOP revisions$0.03-0.15/task
UnstickerRoot-cause analysis when stuck, fresh approaches, lateral thinking$0.05-0.20/task
Error WhispererTranslates cryptic errors into fixes with pattern matching$0.03-0.10/task
Rubber DuckSocratic debugging — forces articulation of the real problem$0.02-0.10/task
PR GhostwriterWrites PR descriptions, commit messages, changelogs from diffs$0.03-0.10/task
Yak-Shave DetectorCatches scope creep — "You started X but now you're doing Y"$0.02-0.05/task
Debt CollectorTracks tech debt, catalogues shortcuts, suggests when to pay down$0.03-0.10/task
Onboarding SherpaLearns new codebases fast — architecture maps, key-file identification$0.05-0.20/task
ArchaeologistExcavates why code exists via git blame and context reconstruction$0.03-0.15/task
Code ReviewerTypeScript/React code reviews for quality, security, accessibility$0.03-0.10/task
ExplorerFast codebase search — finds files, searches code, maps architecture$0.02-0.05/task
Note on costs: These are API token costs charged by the AI provider (Anthropic, OpenAI, etc.), not our fees. You bring your own API key. Enterprise plan customers can run local models (Llama, Mistral) on the server to eliminate these costs entirely.

5-Tier Memory System

Your agent never forgets. Each tier handles a different time horizon, from current session context to permanent learned knowledge.

Session

Scope: Current conversation
Storage: Context window
Keeps: Until session ends

Working

Scope: Active task
Storage: memory.md
Keeps: Pruned weekly

Knowledge

Scope: Learned rules
Storage: knowledge-base.md
Keeps: Permanent (auditor-gated)

Agent

Scope: Per-agent knowledge
Storage: agent-memory/
Keeps: Permanent

Graph

Scope: Structured entities
Storage: MCP knowledge graph
Keeps: Permanent

Archive

Scope: Daily session logs
Storage: daily/ notes
Keeps: Permanent

Automated Workflows

Pre-configured schedules that run automatically. Your agent starts the day with a briefing, monitors health throughout, and wraps up with a summary.

Morning Briefing

7:00 AM daily

Summary of yesterday, today's priorities, pending items

Evening Wrap-up

9:00 PM daily

Archive session learnings, update memory, plan tomorrow

Health Check

Every 6 hours

Verify all agents are responsive, check system health

Knowledge Sync

8:00 AM daily

Process knowledge nominations, update knowledge base, sync Obsidian vault

Key Configuration Files

Every file has a clear purpose. The SOUL.md is what makes your agent unique — it defines personality, values, and communication style based on your onboarding form answers.

AGENTS.md

Defines all specialist agents and their capabilities

SOUL.md

Your agent's personality, values, communication style

USER.md

Information about you — preferences, work style, goals

MEMORY.md

Core persistent memory — carried across all sessions

TOOLS.md

Available tools, APIs, and environment notes

HEARTBEAT.md

Periodic tasks and scheduled check-ins

Want This Set Up For You?

Fill out the onboarding form and we'll configure all 7 layers, 250+ agents, memory system, workflows, and channel connections — customized to your business. Delivered within 48 hours.