ISSUE #002
This week I burned down an OpenClaw deployment and rebuilt the agent runtime from scratch on a Mac Mini. Not because OpenClaw is bad — because I needed to understand every layer. Transport, LLM routing, memory, skills — all of it. The result is a 400-line Node.js harness that can run any agent personality. Twelve articles came out of the process. Here's the best of the week.
THIS WEEK'S FIXES
Build Your Own Agent Harness: A Layer-by-Layer Primer
How to build an always-on AI agent runtime from scratch — transport, personality, LLM routing, skills, memory, and uptime — by validating one layer at a time.obi-jam · infrastructure
Separate the Harness from the Agent
Your agent runtime should know nothing about who it's running. Split machine from mind and every agent gets portable.obi-jam · pattern
Claude for Thinking, Ollama for Doing
Route complex reasoning to Claude API and cheap tasks to local Ollama. Your agent doesn't need its best brain for every message.obi-jam · pattern
Your Agent Is Hallucinating Answers Instead of Running Tools
When command routing fails silently, the LLM fills the gap with confident fabrications. The user never knows the tool didn't run.obi-jam · debugging
Building a Morning Brief: Multi-Source Agent Briefings
How to build a daily agent briefing that pulls from Google Calendar and Vikunja, formats it for Discord, and posts at 6:30am automatically.obi-jam · pattern
Self-Hosted Open Source as Agent Infrastructure
Run Vikunja and Google Calendar locally and your agent gets task management, scheduling, and reminders for $0/month — no SaaS, no vendor lock-in.obi-jam · pattern
Natural Language Date Parsing: The Same-Day Weekday Bug
When your reminder parser sees '~wed 10pm' on a Wednesday, it schedules next week instead of today. A one-character fix.obi-jam · fix
Make Your Agent Transport a Swappable Layer
Define a transport interface once. Discord today, iMessage tomorrow. Your orchestrator should never know which wire it's talking through.obi-jam · pattern
Plus 4 more on the site: conversation memory as context not history, keeping your runtime under 400 lines, why your VPS costs more than the invoice, and Discord markdown gotchas.
"Simplicity is prerequisite for reliability."
— Edsger W. Dijkstra
📊 This week: 12 new articles · 29 total in the library · Most active: agent harness architecture · Frameworks: OpenClaw, Skills, Obi Jam (new!)
— Adam Kinney, building agents at aiallthethings.com
