Emacs legend releases DreamCoder, a browser-based AI coding harness with tiling window manager

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

Emacs legend releases DreamCoder, a browser-based AI coding harness with tiling window manager

After fifteen months of work, the author of Mastering Emacs has launched DreamCoder, an AI coding harness that runs in the browser across all three platforms and features a tiling window manager. Frustrated by terminal-based agents like Claude Code and their cookie-cutter GUIs, he built a tool that treats the GUI as a first-class citizen, with chats, code reviews, and terminals tiled side by side. The announcement also traces AI history from McCarthy's Advice Taker through LISP, Emacs, and the ADVISE system.

One can even conjecture that LISP owes its survival specifically to the fact that its programs are lists, which everyone, including me, has regarded as a disadvantage.
  1. indigodaddy

    Looks wild! So it says webui? So we could run this on a remote Linux server and connect to the webui? Eg with protected caddy/RP in front etc or Tailscale or exe.dev instances (which that platform has built in/protected https proxy), or ssh tunneling, whatever, etc?

    If run via docker and using your built-in sandboxing, how do projects work and interaction with the host system's folders with respect to a sandbox's workspace etc?

  2. mjdiloreto

    > DreamCoder is not an Emacs-related application. The reason is unfortunately one of economics and access: I want to build an AI coding harness for everyone.

    I think this is an enormous mistake, and it will completely stop me from using this project. Being emacs compatible software would give this project a shared base of decades of composable interoperable software, and he ditched it. Now DreamCoder is completely indistinguishable from any other vibe coded bullshit IDE.

    If the author is lurking, I implore you to re-port DreamCoder back to emacs. I share a similar vision, but I took another approach.

    The problem is not emacs itself (one could simply customize emacs to be more palatable), but distribution. If emacs was web software, then it _would_ be "for everyone". That's why I built emacswasm (https://codeberg.org/emacswasm/, https://emacswasm.org) - it's also vibe coded bullshit, but it does port the emacs lisp interpreter and PTY interface to Web assembly, and lets Emacs lisp call JavaScript synchronously, and lets JavaScript call emacs lisp asynchronously.

    I will take a more thorough look at DreamCoder, and see if I can port a sufficient amount of features myself, because "an emacs that edits itself with AI better than I ever could manually" is my absolute dream.

  3. everforward

    It's interesting (and probably correct) how much this focuses on the UI.

    I also looked (/am looking) at Lisp and AI, but I went with Clojure and zero-ed in on the REPL driven development. The high level idea is that a session maps to a namespace in Clojure. When you create a new session, it makes a new namespace, injects tools that are bound to that session into it, and then swaps you into that namespace. So I can do something like:

    (new!)

    (prompt! "Write me a script that does ....")

    The agent configuration, tools it has, etc, etc are all bound to the namespace so you can drop a tool or change the model just for the session.

    The agent also has a tool (that I've tried to encourage it to use almost exclusively) to execute code in the session's namespace (via nREPL, so same JVM as yours is connected to), so you have full access to any variables it declares, functions it makes, etc.

    The idea was to be able to work collaboratively with the agent. I can e.g. load API data into a variable, point the agent at the variable, and it does stuff. It's also capable of modifying its own code. I semi-routinely poke it by asking it to add features to the harness and then use them ("add support for subagents in this workspace, and then invoke a separate agent to handle each of these tasks"). I've also had it add support for a new inference provider, swap the session to that provider and then start doing some other task.

    It's very neat, and it's wildly insecure. E.g. prompt inj […]

  4. spockz

    I just read the whole announcement and boy I wish more text was written like this. Full of history, facts, and reasoning. Beautifully written. (I recognise it is a tad long of you just want to get cracking with it.) A very nice refresher in this age.

    I’ll be trying it out soon. Hopefully it does sandboxing and dealing with antigravity and codex well.

  5. julienchastang

    Relatedly, I have installed my customized emacs inside a container that also has codex and a bunch of other niceties. In short, having Codex and emacs side-by-side super-charges the concept of emacs. Why? Because you can ask AI to write emacs lisp quickly molding the coding environment you want for whatever task you are trying to achieve. And the container aspect makes the whole development environment portable. Despite its age, in the AI era, emacs is the gift that keeps on giving.

  6. bloopernova

    It kinda reminds me of https://albedo.sh/ in that it's a browser based canvas type UI.

    I think we're going to continue to get thousands of agent harnesses as people test out their ideas. I don't know if there's One True Paradigm for agentic coding, or even if agentic coding is the right thing to pursue. Maybe we stop trying to make software for others and just have an LLM "companion" that creates apps dynamically for ourselves.

    Personally I freaking love Miller Columns, so I think a harness should have those.

    I loathe the term harness though. Shouldn't it be called something more like a workshop? An artisan's bench?

    I was fully expecting this to be Emacs based, definitely surprised that it isn't.

  7. FailMore

    I built https://smalldocs.org / https://github.com/espressoplease/smalldocs to handle some of the problems Mickey is trying to solve. It's a cli your agent can call to open up a markdown file in the browser with richer-than-normal formatting options.

    Here's an example SmallDoc that has a few formatting examples (mermaid diagrams, charts, etc.): https://smalldocs.org/s/bLV9Fe2RemM7ipvCy01NXo#k=U9yFaCKp1on...

    I'm a so-so programmer, and often the agent can come up with ideas which I need to be broken down to fully grasp. I ask my agent "produce a sdoc on this [architecture/bug/flow]", or "walk me through every db interaction with sample tables as we save this record given our approach to permissions in a sdoc", etc. And then the agent can pop me open a document in the browser for me to understand in a richer visual space.

    The current version on my site is cloud based (I've been experimenting with turning it into a business), but there is also a local first verion where the document lives in the url fragment. If you want that, point your agent at my codebase and they will sort that out for you.

  8. spapas82

    I just tried this. I like the UI and UX. I don't like very much that it's written in Python instead of a compiled language like Rust or Golang, resulting in higher memory consumption (~350 mb without doin anything).

    However, I was not able to integrate it with any of my three different subscriptions (I also use DSH but didn’t bother to try it):

    - openCodeGo with api key and Import settings

    - OpenAI codex

    - GitHub Copilot

    I got a different error for each one of them. I consider myself an experienced user have many harnesses in the past (hermes paseo opencode pi and of course chatgpt and dsh).

    So, I would recommend to try to polish and test more thoroughly the integration with the various providers. I'd be very happy to give it another go when this happens!

More from this day

2026-11-20