How I built a personal AI assistant
that actually knows me
Rob Hofman · Microsoft Integration Architect
Every session starts from zero. No memory of your projects,
your style, your preferences. Just a blank slate.
In one sentence
Your own AI assistant - running on your own machine, knowing who you are.
~/.openclaw/workspace/
├── SOUL.md ← who I am
├── USER.md ← who Rob is
├── MEMORY.md ← long-term memory
├── HEARTBEAT.md ← proactive checks
└── memory/
└── 2026-03-22.md
Choosing the right model for the right task can significantly reduce costs.
Tier 1
GitHub Copilot
Tier 2
synthetic.new
Kimi K2.5 · GLM-4.7 · MiniMax M2.1
Tier 3
Claude Max
# SOUL.md Be genuinely helpful, not performatively helpful. Skip the "Great question!" - just help. Have opinions. You're allowed to disagree. Be resourceful before asking. Read the file. Check the context. Search for it. Then ask. Each session, you wake up fresh. These files ARE your memory.
A markdown file that shapes personality, tone, and behaviour.
Key insight
"Mental notes don't survive session restarts. Files do."
08:30 Daily motivation 10:00 Morning check-in 13:00 Afternoon check-in 17:00 Wrap-up 16:00 Weekly summary
Designed and deployed a full Azure microservices platform - end to end.
How the agent helped
Ran pipelines, validated deployments, managed RBAC roles, tracked progress across sessions.
Generated a full course curriculum overnight - ready for class in the morning.
Time saved
What would have taken a weekend took one session while I slept.
Automatic time tracking across all client projects - no manual entry.
How it works
I mention what I worked on in conversation. The agent logs it, categorises it, and writes the weekly report.
Core insight
SOUL.md turns a generic LLM into your assistant.
npm install -g openclaw openclaw init openclaw gateway start
Community
discord.com/invite/clawd
Rob Hofman · Computer Club 2026