
310 - Mitchell Hashimoto on Ghostty & His Agentic Coding Workflow
About this episode
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.
Full shownotes at fragmentedpodcast.com.
Show Notes
Ghostty
- Ghostty - Mitchell's fast, native terminal built for platform integration across Mac and Linux
- Terminal shell
- SSH - secure shell
- PTY - pseudoterminals
- Terminal Multiplexers
- tmux - most popular open source one
- XTGETTCAP by xterm
- libghostty - the cross-platform terminal emulation library that powers Ghostty's core
- xterm-js - powers terminal for apps like VSCode and the cloud
- Jedi Term - Intellij's embedded terminal
- Ghostty is now a non-profit
- cmux - native macOS terminal
multiplexer built on libghostty — a fork Mitchell champions - Free Software Definition -
the 4 essential freedoms- The freedom to run the program as you wish, for any purpose.
- The freedom to study how the program works, and change it to make it do
what you wish. - The freedom to redistribute copies so you can help others.
- The freedom to distribute copies of your modified versions to others.
- Mitchell's tweet on unsolicited PRs and transfer of ownership
The AI Adoption Journey
- My AI Adoption Journey -
Mitchell's blog post outlining his five-step framework - Step 1: Drop the Chatbot
- Episode 301 - AI Coding ladder - Different stages of AI
adoption
- Episode 301 - AI Coding ladder - Different stages of AI
- Step 2: Reproduce Your Own Work
- Step 3: End-of-Day Agents
- OpenAI Deep Research -
kick off research tasks for a "warm start" the next morning - Spine AI research - deep research tool for
longer, hour-long analysis tasks
- OpenAI Deep Research -
- Step 4: Outsource the Slam Dunks
- Step 5: Engineer the Harness
- Episode 307 - Harness Engineering - Fragmented's deep dive
on harness engineering, heavily inspired by Mitchell's post
- Episode 307 - Harness Engineering - Fragmented's deep dive
- Step 6: Always have an Agent running
- Peter Steinberger
- Codex plugin for Claude Code
Get in touch
We'd love to hear from you. Email is the best way to reach us or you can check our contact page for other ways.
We want to hear all the feedback: what's working, what's not, topics you'd like to hear more on.
Co-hosts:
[!fyi] We transitioned from Android development to AI starting with
Ep. #300. Listen to that episode for the full story behind
our new direction.
Get every episode summarized
Each time Fragmented - AI Developer Podcast publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from Fragmented - AI Developer Podcast

311 - Self learning harnesses are here
Fragmented - AI Developer Podcast

309 - Background Agents
Fragmented - AI Developer Podcast

308 - How Image Diffusion Models Work - the 20 minute explainer
Fragmented - AI Developer Podcast

307 - Harness Engineering - the hard part of AI coding
Fragmented - AI Developer Podcast