What does it take to keep an agent working after its process dies? Pi creator Mario Zechner and Earendil co-founder Armin Ronacher join KG to explain Pi Durable: explicit tasks, crash recovery, and the primitives for multiplayer agents. We also dig into why Pi added MCP and codemode, and why a harness that can rewrite itself still needs a clear goal.

Full shownotes at fragmentedpodcast.com.

Claude Code and Codex have been the mainstay agent harnesses, with OpenCode and Pi as the popular open-source alternatives. But two new entries are pushing what a harness even is: DeepSeek’s Cordis kernel, where everything — down to the agent loop itself — is a plugin you can hot-swap at runtime, and Prime Agent, an RLM-based harness that treats sub-agents and context as function calls in a live REPL. We break down what actually makes each one different.

Full shownotes at fragmentedpodcast.com.

Mitchell Hashimoto co-founded HashiCorp, built some of the most impressive DevOps tools like Vagrant and Terraform, sold the company to IBM — and then built a terminal. Ghostty is now where a huge chunk of agentic coding actually happens. Mitchell was an AI skeptic. We walk through his six-step adoption framework and the workflows he uses day to day — warm-start research, Hail Mary prompts across twenty GitHub issues, and knowing when to let the agent slam dunk it.