Learnings from post-AI Open Source and how we’re approaching this so far.
written on May 24, 2026
Pi is now part of Earendil, but in the important sense it is
still Mario’s project. He has been living with its
issue tracker longer than I have, and he has been exposed to the weirdness of
the new form of agent traffic in Open Source projects for longer too. This post
I Built an AI That Decides Which AI to Talk To — Running 24/7 From My Living Room
Tools I'm Using in 2026 (and what I've stopped using from 2025)
I Built a 'Production-Ready' AI Agent Framework. It Was a Lie. So I Fixed It.
Putting Claude Code Under Version Control: Configs Since July, Memory Since April
I built an open protocol to make AI coding agents follow senior-engineering workflows
I gave an AI a Kill Switch. Here's what I learned about trust in local-first tooling.
Five things that caught my attention this week in AI tools and open-source models
What I'd do differently if I migrated this CI/CD pipeline again next week
From an Abandoned Hackathon Project to an AI Study Workspace 🚀
I Built a Local AI Gateway That Talks to Claude, ChatGPT, DeepSeek and Gemini — Without a Single API Key
Mario Zechner, creator of Pi, joins Armin Ronacher to explore AI coding’s limits, arguing that human judgment still matters most…
Exploring Pi's ability to read its own documentation, understand its codebase, and help extend or modify its behavior through…
Last Saturday when I woke up, my AI agent reviewed 14 restaurant ratings in Indiranagar, updated a...
Introduction In some ways, a lot has changed since my last post, and in other ways, not...
I Built a "Production-Ready" AI Agent Framework. It Was a Lie. So I Fixed It. A story...
When you let an AI agent share your machine for a year, you eventually hit a question you can't...
