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

facundo_olano 165 points 36 comments November 20, 2026
www.masteringemacs.org · View on Hacker News

Discussion Highlights (14 comments)

weavermarquez

Oh, that's exciting! I have been disappointed by Steve Yegge's attempts at emacs-inspired coding harnesses, and options like ECA using ACP have always felt a little too behind for me, so I honestly felt like an insistence on sticking with Emacs for coding / AI interfacing was actually holding me back. But I'm certainly excited to see what Mr. Mastering Emacs has to say about it. One request, which I'm emailing in for: arm64 builds for Linux, since I use Asahi.

rthimian

That really looks interesting. Both in terms of functionality and in terms of the visual design. Refreshingly different.

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.

hasbot

Should have linked to the actual harness and not some incredibly long article: https://www.dreamcoder.ai/

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 injection could theoretically make the LLM change itself to hide messages from you, there's nothing to prevent that. I'm actually not sure how you'd even go about trying to secure that, which is why it's probably a terrible idea. Fun, though.

2001zhaozhao

FINALLY someone else made an orchestrator with a built-in desktop. This is the right direction for managing agents for sure.

doginasuit

How is this so beautiful? Both the article and the IDE. Really refreshing design.

cmrdporcupine

Runs locally... but requires account registration to get a license and requires signing a EULA? Eh. This is a saturated market.

chilicuil

it seems it doesnt work with the antrophic suscription model, nice project to try later

Uptrenda

The aspergian obsession of making 1000 different versions of the same thing. "Bruhh this wheel is going to be more of a good wheel than all the other wheels bruhh. I consider it a good use of my time compared to working on original problems." Almost as heart warming as the people porting every code base between languages because of their strange religious / cult beliefs. I am angry. Before anyone says I'm hating for no reason: does anyone here have an issue with the existing tools? Does it not already do more than enough? Can the most basic interface that exists already do what you need? Did author ask anyone before building it?

keyle

I read the whole thing and the argument is long to come as to why this is superior to other harnesses; and it appears to come down to "I have taste" therefor "this is better" because I said so. No actual metrics and something very much in the feels of Omarchy. Thank you for your closed contribution to humanity, I guess. Release the source.

wangguode

Owning the harness rather than treating the model as a magic black box is where all the real reliability gains come from. Two primitives that made the biggest difference in our own agent harness: 1. Pre-tool AST/command boundary checks before execution rather than relying on system-prompt warnings. 2. Aggressive stdout/stderr truncation (capping tool output tokens before context bloat triggers silent instruction drift). Curious how DreamCoder handles long-running test output or background server logs inside the Emacs buffer loop without blowing up context.

jeffybefffy519

Mehhh i dunno, this seems like it missing a key point of actually make agent outputs reviewable.... thats whats missing.... and chatting to an agent to do tasks isnt the right input is what i feel.

esFran

Very interesting, in deed. I think it is one of the correct ways to harness all the power of AI. A set of workers doing your job in a very clear way.

Semantic search powered by Rivestack pgvector
13,334 stories · 126,150 chunks indexed