Artificial Intelligence1 min read

DreamCoder: Coding harness and IDE from the author of Mastering Emacs

By · Published by Everything Blog

In short

The project was initiated in May 2025 after its creator experimented with Claude Code to generate enterprise middleware. While appreciating the underlying system's rapid cross-language versatility, the developer determined that typical chat panels fail to meet complex programming demands. Following iterative backend work and a completed beta phase, the platform is now formally available. The initiative aligns itself with the computing lineage of LISP, which Steve Russell first made functional via an S-expression interpreter.

Key points

  • The new harness replaces common chat-pane layouts with an environment optimized for serio…: The new harness replaces common chat-pane layouts with an environment optimized for serious developer workflows.
  • Claude Code demonstrated considerable versatility across languages but exposed limitation…: Claude Code demonstrated considerable versatility across languages but exposed limitations in existing terminal-based programming setups.
  • The project roots its modern development philosophy in the foundational computing history…: The project roots its modern development philosophy in the foundational computing history of McCarthy and Russell.

Sources checked by our analysis pipeline: 1

It’s been a little bit quiet around these parts; sorry about that. I’ve been really busy for the past fifteen months with a major project that I am finally ready to formally release. So I’d like to talk about that project, and also a potted history of AI and Emacs.

It’s called DreamCoder, an AI coding harness that is very different from the ones you’re probably familiar with already.

I installed Claude Code a few days after its first release some time in May 2025. I put some coins in the slot machine and I put it to work building a complex piece of enterprise middleware I’d built several times in my career. Wow.. watching this thing chomp its way through the project with that chaotic, early Sonnet energy. It was far, far from perfect; it required a lot of human steering, input and correction, but the speed advantage was undeniable, and seeing it jump between disparate programming languages, frameworks and theoretical and practical programming from one turn to the next was just such a sight to behold.

One thing…

Artificial Intelligence