AI Dream Team — Full Setup Guide

What happened, what we decided, why, and how to build yours
AZ Rollin — March 3, 2026

What's In This Guide

  1. The Story — What Happened
  2. The Problem We Hit
  3. The Big Decision — Which AI Brain?
  4. The Dream Team — All 11 Agents
  5. Model Routing — Who Gets What Brain
  6. Step-by-Step: Get Your API Keys
  7. How to Activate Everything
  8. Real Costs Breakdown
  9. Quick Reference Card

1. The Story — What Happened

Here's what went down in one session:

1 Installed Docker Desktop — the "building" where our AI team lives.

2 Installed Ollama — a free AI brain that runs directly on my Mac (M3 Max, 48GB RAM). No internet needed. No monthly fees. Zero cost.

3 Deployed OpenClaw — the "office" where AI agents work. Runs 24/7 in Docker.

4 Created MAYA & OLIVER — my first two agents. MAYA handles priority tasks (named after my niece, age 8). OLIVER handles support tasks (named after my nephew, age 5). They cross-check each other on important decisions.

5 Secured the dashboard — changed to a random port, locked it to localhost-only, added token authentication + device pairing.

6 Hit a wall — the free AI brain (Llama 3.1 8B) was too small for agent work. It broke in weird ways...

2. The Problem We Hit

Llama 3.1 8B (the small free model) couldn't handle agent work.

Why? Running an AI agent is WAY harder than just chatting. The agent needs to:

An 8-billion parameter model just doesn't have enough "brain power" for that. It's like asking an intern to be CEO.

The lesson: Free local AI is amazing for simple tasks (drafting, summarizing, quick research). But for running a team of agents? You need more power.

3. The Big Decision — Which AI Brain?

We researched every option. Here's what we found:

OpenAI API
(GPT-4o)

$3-10/day

$90-300/month
Smartest option
Also most expensive

DeepSeek V3
(API)

~$0.30/day

~$9/month
95% cheaper than GPT-4o
Nearly as smart

Ollama 70B
(Local/Free)

$0/day

Free forever
Needs 40GB+ RAM
Slower, offline backup

OUR DECISION: DeepSeek V3 as Primary Brain

Why DeepSeek?

Bottom line: When you're bootstrapping, spending $9/month instead of $150/month means you survive longer.

The backup plan: Ollama with Llama 3.1 70B (40GB model) is still downloading. Once it finishes, it becomes our free offline backup — agents can still work when the internet goes down or if we want to save every penny.

4. The Dream Team — All 11 Agents

Two are live. Nine more are designed and ready to deploy when needed.

LIVE NOW

👑

MAYA — Lead Manager

Named after AZ's niece (age 8). Sharp, organized, no-nonsense.

ACTIVE Priority tasks, content pipeline, revenue tracking, daily action-log review. Makes the big calls. Always cross-checks with OLIVER before approving anything major.

🔍

OLIVER — Support Manager

Named after AZ's nephew (age 5). Curious, thorough, catches what others miss.

ACTIVE Light tasks, cross-checks MAYA's decisions, quality control, security watchdog. The safety net. If MAYA says "go," OLIVER double-checks before we actually go.

COMING NEXT (Deploy When Ready)

🧭

SCOUT — Research Agent

Deep researcher. Finds trends, competitors, opportunities.

PLANNED Web searches, competitor analysis, trend tracking, market research. Reports findings to MAYA.

📝

ECHO — Content Writer

Writes in AZ's voice. Drafts, scripts, captions, descriptions.

PLANNED Episode scripts, YouTube descriptions, social captions, email drafts. Never posts — always drafts for AZ's approval.

💰

DOLLAR — Finance Agent

Tracks every dollar. Budgets, forecasts, affiliate revenue.

PLANNED Revenue tracking, expense logging, affiliate commission monitoring, financial forecasting. Reports to MAYA.

🚀

BOOST — Social Media Agent

Engagement optimizer. Hashtags, timing, analytics.

PLANNED Social media scheduling recommendations, hashtag research, engagement analytics, cross-platform strategy. Draft-only.

🔨

BUILDER — Dev Agent

Codes tools and automations. The engineer.

PLANNED Builds custom tools, scripts, automations, web pages. Gets the smartest brain (Claude Sonnet) because coding needs precision.

✂️

CLIPPER — Video Clips Agent

Finds viral moments. Suggests cuts and shorts.

PLANNED Analyzes video transcripts, suggests clip timestamps, writes shorts descriptions. Works with ECHO on content pipeline.

📡

RADAR — Analytics Agent

Monitors everything. Launch readiness, metrics, alerts.

PLANNED Launch monitor, YouTube analytics, social metrics, trend detection. Alerts MAYA when something needs attention.

🌍

BRIDGE — Translation Agent

4 languages. Localizes content for global reach.

PLANNED Translates content into Azerbaijani, Russian, Turkish. Adapts tone for each culture, not just word-for-word translation.

💡

PULSE — Audience Agent

Understands the audience. Comments, feedback, sentiment.

PLANNED Monitors comments/feedback, gauges audience sentiment, suggests content adjustments. The "finger on the pulse."

5. Model Routing — Who Gets What Brain

Not every agent needs the same power. That's how you keep costs low. It's like hiring: you don't pay intern rates for a CEO, and you don't pay CEO rates for filing paperwork.

Agent(s) AI Model Why This Model Cost
MAYA, OLIVER DeepSeek V3 Smart enough for management decisions. 95% cheaper than GPT-4o. ~$0.30/day
ECHO, BOOST, CLIPPER, PULSE DeepSeek V3 Writing and content work. DeepSeek handles it well. ~$0.15/day
SCOUT, RADAR, DOLLAR DeepSeek V3 Research and analysis. Good with data processing. ~$0.10/day
BUILDER Claude Sonnet 4.6 Coding requires the smartest model. Sonnet is the best coder.
BRIDGE DeepSeek V3 Translation quality is excellent in DeepSeek. ~$0.05/day
ALL (backup) Ollama / Llama 3.1 70B Free offline fallback. When internet is down or saving money. $0

Total estimated daily cost (full team running): ~$1-2/day ($30-60/month)
Compare to running everything on GPT-4o: $10-20/day ($300-600/month).
That's 85-90% savings.

6. Step-by-Step: Get Your API Keys

A. DeepSeek API Key (Primary — Get This First)

1 Go to platform.deepseek.com

2 Click "Sign Up" — use email or Google account

3 Once logged in, go to API Keys (left sidebar)

4 Click "Create API Key"

5 Give it a name like openclaw-team

6 COPY THE KEY IMMEDIATELY — it starts with sk- and you can only see it once!

7 You get 5 million FREE tokens on signup — no credit card needed

Cost: $0 to start. When free tokens run out, add $5-10 credits. At ~$0.30/day, $10 lasts about a month.

B. Anthropic API Key (For BUILDER Agent — Optional, Later)

1 Go to console.anthropic.com

2 Sign up or log in (this is SEPARATE from your Claude Max subscription)

3 Go to API Keys → Create one named openclaw-builder

4 Add $5 credits to start

NEVER connect your Claude Max subscription to OpenClaw. That violates Anthropic's Terms of Service and WILL get your account banned. The API (console.anthropic.com) is a completely separate product — that's allowed.

C. Ollama 70B (Free Backup — Already Downloading)

The Llama 3.1 70B model (~40GB) is currently downloading on your Mac. Once it finishes, it becomes a free offline backup. No API key needed — it runs on your machine.

Check status: ollama list in Terminal

7. How to Activate Everything

Once you have your DeepSeek API key, give it to Claude Code in Terminal and say:

"Here's my DeepSeek API key: sk-xxxxx. Add it to OpenClaw and switch MAYA and OLIVER to DeepSeek V3."

What Claude Code will do:

  1. Add DeepSeek as a model provider in ~/.openclaw/openclaw.json
  2. Switch MAYA and OLIVER from Ollama to DeepSeek V3
  3. Keep Ollama as fallback (free backup)
  4. Restart the gateway
  5. Test both agents with fresh sessions

For each new agent (SCOUT, ECHO, etc.), just tell Claude Code:

"Add SCOUT as a research agent using DeepSeek V3."

Claude Code will create the agent's workspace, personality file, and register it in the config. Takes about 2 minutes per agent.

8. Real Costs Breakdown

What Cost Notes
OpenClaw (Docker) Free Open source, runs on your Mac
Ollama + Llama models Free Local AI, no internet needed
DeepSeek V3 API ~$9/month 5M free tokens on signup, then ~$0.30/day
Anthropic API (BUILDER only) Only when coding. Skip until needed.
Claude Code (Terminal) $0 extra Included in Claude Max subscription
Telegram Bot Free Already running

Total Monthly Cost to Run the Dream Team

Minimum (MAYA + OLIVER only) ~$9/month
Full team (all 11 agents, no BUILDER) ~$30/month
Full team + BUILDER (Claude Sonnet)

Compare: Running this on GPT-4o alone would cost $300-600/month.

9. Quick Reference Card

WhatDetails
Open Dashboardhttp://localhost:YOUR_PORT
Start OpenClawcd ~/openclaw && docker compose up -d openclaw-gateway
Stop OpenClawcd ~/openclaw && docker compose down
Check healthcd ~/openclaw && docker compose logs --tail 10 openclaw-gateway
Restart after config changecd ~/openclaw && docker compose restart openclaw-gateway
Talk to MAYADashboard → Chat → select MAYA → New session
Talk to OLIVERDashboard → Chat → select OLIVER → New session
Check Ollama modelsollama list
Config file~/.openclaw/openclaw.json
Docker env~/openclaw/.env
MAYA's personality~/.openclaw/workspace-maya/SOUL.md
OLIVER's personality~/.openclaw/workspace-oliver/SOUL.md
Shared brain files~/.openclaw/workspace/company-brain/

API Dashboards

ProviderDashboardWhat to Check
DeepSeekplatform.deepseek.comToken usage, remaining credits, API keys
Anthropicconsole.anthropic.comAPI usage, billing, rate limits
Ollama (local)ollama list in TerminalDownloaded models, status

Key Decisions Log

DecisionWhat We ChoseWhy
Primary AI BrainDeepSeek V3 API95% cheaper than GPT-4o, smart enough for agents, 5M free tokens
Backup AI BrainOllama / Llama 3.1 70BFree, offline, runs on M3 Max. Insurance policy.
Coding Agent BrainClaude Sonnet 4.6Best coder available. Only used when BUILDER needs it.
Dashboard PortRandom (assigned at install)Security — default ports are targeted by bots
Network Binding127.0.0.1 onlyOnly YOUR Mac can access the dashboard. No outside access.
Agent SafetyMAYA ↔ OLIVER cross-checkTwo agents verify each other. Built-in safety net for big decisions.
CommunicationDraft-only modeAgents NEVER send messages directly. Always drafts for AZ's approval.