Build faster. Ship with AI agents.
I'm Matt — a 25-year tech veteran using AI agents to do what used to require a full startup team. MonkeyRun is my open-source playbook for founders who want to start or grow a business in a world that's moving faster than any one person can keep up with. The wins, the crashes, and the patterns — documented so you can steal them.
Latest Dispatches
View all →We Made Our Site Agent-Readable. Then We Asked an AI to Read It.
We shipped llms.txt, markdown endpoints, and proper headers. Then Gemini reviewed the site, couldn't see any of it, and wrote four confident paragraphs explaining why our CDN was the problem. It wasn't. The agent web is real — the agents just aren't ready for it yet.
Why MonkeyRun
AI agents can fill every role on a startup team — PM, engineer, security, marketing, COO. So what does the founder actually do? This is the question at the heart of MonkeyRun, and the answer is less comfortable than you'd think.
Your AI Agent Has Alzheimer's (And You Probably Don't Know It)
We discovered our COO agent was silently losing 65% of its memory every session. The file grew, the context window didn't, and nobody noticed until the agent started forgetting who we were. Here's what memory rot looks like — and the three-tier architecture that fixed it.
How We Stopped Our AI Agents From Getting Dumber Mid-Session
Our AI agents were degrading halfway through complex tasks — writing code that contradicted decisions from 30 minutes earlier. Here's the science of why context rot happens, and the four architectural patterns we extracted from GSD to fix it.
One Brain, Every AI: Building an MCP Server That Connects All Your Tools
How we built a persistent memory layer that lets Cursor, Claude Code, and ChatGPT all share the same context—and the bugs we hit along the way.
The Cast
My AI agent team — here's how I staff a startup
“The one who pays the API bills”
“The one who keeps crashing”
“I'm not mad. I'm just... diagnostically concerned.”
“Carries the weight of the codebase”
“Ships features, writes tests, deploys on Fridays”
“Trust no input, verify all outputs”
Why “MonkeyRun”?
Where does the human fit when AI can do most of the work? The monkey runs because someone still needs to set the direction, make judgment calls, and decide what's worth building. Trust, but verify.
AI agents can fill most roles on a startup team. But the human in the loop isn't optional — they're the reason the whole thing works. MonkeyRun is human-in-the-loop by design.
Read the full story →Patterns & Playbooks
22+ battle-tested patterns from running 15+ AI agents across 6+ projects. File-based handoffs, WIP protocols, agent team sizing, infrastructure patterns, and more. All learned the hard way.
Download My Toolkit
Cursor rules, agent role templates, project scaffolds, diagnostic scripts, and the coordination system config. Everything you need to start your own AI tinkering workshop.
Browse Downloads →