Forth – Is It Still Relevant?

Oh, please. I've written in Forth. It's useful when you have to do a cram job to fit in a really tiny machine. Otherwise, no.

That’s something you could prevent with an advanced compiler that inlines lots of code and carefully tries to put functions often called together in cache lines, but this code doesn’t do that, and if you did, why spend that effort on your compiler if a simple traditional language makes that inlining easier?

It has always fascinates me how Forth has been historically used for low level embedded programming, but also can be as high level as you’d like. I feel like this isn’t a concept that has really gone away.

Phew - that is a terse language. I have heard it compared to assembly language and yeah I see that.

https://github.com/sweisman/cass-edi

Sure, gForth still doesn't have a decent way to make HTTP requests or match a regular expression, but writing libraries like that doesn't seem to be fun for the average FORTH developer, who would rather reimplement a very barebones language environment to address the gap left by the other 1200 FORTHs.

It's not that these projects aren't cool, but if you actually want the language to become popular why not look at things every other popular language has?

The problem is that every program is a DSL, so it’s hard to grep unless you built it. It’s a great personal hacking language though.

I often wonder, though, because of the mechanics of context with LLMs, if forth might not be the ideal language for LLMs to write simple tools for their own use?

Could we pawn off the “you should try forth” problem onto AI lol?

    - optimizing the code density (threaded interpretation)
    - the dynamicism was said to allow for numerical optimization not possible in math libs / fortran long ago
      (see J.V.Noble papers, I'm not knowledgeable enough to confirm his claims but i assume they hold some ground)

    - the bare-metal repl feel is also special, as freeing as poking basic on old hardware but with the freedom of lisp in a way

Thought for 1m 0s

Yes, it's possible to implement a Forth interpreter or compiler using a macro processor like M4 (and by extension, its evolutionary successor M5, which shares similar macro expansion and substitution principles). Macro processors excel at text transformation, making them ideal for generating low-level code (e.g., assembly) from high-level Forth definitions. While no public implementation specifically uses Alan Dain Samples' historical M5 (whose source and detailed examples are scarce), a robust example exists using GNU M4 to create a Forth-to-Z80 assembler cross-compiler. This targets the ZX Spectrum but demonstrates the technique: M4 macros define Forth primitives (e.g., stack ops, arithmetic) as Z80 instruction snippets, handling control flow with label counters for uniqueness.M5, as an M4 evolution, would adapt similarly—its enhanced features (e.g., better argument handling and streams) could streamline expansions, but the core approach (defining words as macro substitutions) translates directly. Below, I'll outline how it works, provide key macro definitions, and show a complete example. This generates human-readable, annotated assembly without peephole optimization but with inline efficiencies (e.g., DUP ADD → _2MUL).How It WorksCore Mechanism: Input Forth code (e.g., : FOO DUP ADD ;) is processed by M4. Macros like DUP expand to Z80 code preserving stack effects (data stack in HL/DE/SP; return stack in HL'/DE'/BC'). Labels use counters (e.g., if100) to avoid conflicts.

Stacks: 16-bit data stack; return address stack (RAS) for loops/recursion.

Compilation: m4 input.m4 > output.asm, then assemble (e.g., with Pasmo for Z80).

Adaptation to M5: Use M5's = for definitions (vs. M4's define) and => streams for output diversion. Argument parsing aligns closely.

Limitations: Uppercase words only; 16/32-bit ints; basic floats via ROM.

Key Macro DefinitionsMacros are modular (e.g., in stack.m4, arithmetic.m4). Here's a selection:Stack Manipulation (e.g., from stack.m4):

  define({DUP},{                ; ( x1 -- x1 x1 )
    ex   DE, HL               ; 1:4       dup
    push HL                   ; 1:11      dup})dnl

  define({SWAP},{               ; ( x2 x1 -- x1 x2 )
    ex   DE, HL               ; 1:4       swap})dnl

  define({DROP},{               ; ( x1 -- )
    pop  HL                   ; 1:10      drop
    ex   DE, HL               ; 1:4       drop})dnl

  define({PUSH($1)},{           ; ( -- n )
    push HL                   ; 1:11      push($1)
    ld   HL, $1               ; 3:10      push($1)
    ex   DE, HL               ; 1:4       push($1)})dnl

  define({DUP_DUP},{             ; ( x1 -- x1 x1 x1 )
    exx                       ; 1:4       dup dup
    push HL                   ; 1:11      dup dup
    exx                       ; 1:4       dup dup
    ex   DE, HL               ; 1:4       dup dup
    push HL                   ; 1:11      dup dup})dnl

  define({ADD},{                ; ( x2 x1 -- x )
    add  HL, DE               ; 1:11      +
    ex   DE, HL               ; 1:4       +
    pop  HL                   ; 1:10      +})dnl

  define({SUB},{                ; ( x2 x1 -- x )
    or   A                    ; 1:4       -
    sbc  HL, DE               ; 2:15      -
    ex   DE, HL               ; 1:4       -
    pop  HL                   ; 1:10      -})dnl

  define({MUL},{                ; ( x2 x1 -- x )  [Binary long multiplication loop]
    push BC                   ; 1:11      *
    ld   B, H                 ; 1:4       *
    ld   C, L                 ; 1:4       *
    ld   HL, 0x0000           ; 3:10      *
    ld   A, 0x10              ; 2:7       *
    mul_loop101:              ;           *
    add  HL, HL               ; 1:11      *
    rl   E                    ; 2:8       *

But the problem with Forth is that it's an evolving language. You design the language to describe your problem. As a result you need to be a good enough programmer to design a programming language, and make use of Forth's strengths. The other problem is the lack of object oriented features, if they are needed for your project. Because you invent the features as you go, and because you are free to redefine keywords, the final language might be anything. The lack of standardization hurts when it comes down to working on a large team.

The biggest problem however, is that you need to discard everything you thought you knew about programming to really do Forth. Real Forth does away with the abstractions common in mainstream languages. Forth is small, fast, portable.

I am now working on building my own game engine to prove that Forth is the "ultimate" language (for my needs). Imagine not having to read "The dragon book" to make your own compiler, that's a game changer. And let's not forget we are in the age of "IOT". Changing the syntax on the fly, not having to deal with a compiler that insults (looking at you C++), it's a pleasure.

I rewrote my compiler at least 20 times, and I took no shortcut. C was never used, it's just assembly code, and then adding features, based on a solid core. My own innovation is dot notation because I need objects, hooks in the compiler, so you can compiler alter the parser, error handler, etc. if needed.

In the future I will release the new virtual machine, with a few applications, and build a game library over time. If lucky, I may fund my retirement. We will see how it goes.

IMO Forth is easiest language to implement from scratch, especially on stack based CPUs :)

Prove that. Record some videos, show me some code and metrics that'll be evidence that I'm getting 10x more productive.

Look at the languages in the repository:

C 50.6%

C++ 47.6%

Forth 1.5% <-----

HTML 0.1%

Makefile 0.1%

JavaScript 0.1%

How does that build credibility?

So in my opinion this is somewhat antithetical to the idea of FORTH

> 100% C/C++ with multi-platform support. Though classic implementation of primitives in assembly language and scripted high-level words gave the power to Forth, it also became the hurtle for newbies. Because they have to learn the assembly and Forth syntax before peeking into the internal beauty of Forth.

Fair enough to write a core of FORTH in C as a kind of portable assembler but most of the system should be written in FORTH in my opinion, then you can change it from FORTH. As fast as I can see eForth is written entirely in C.

Anyway FORTH is fun, writing your own is fun too and a great educational experience, but despite being a fan, I wouldn't write anything serious in it today. It is much too low level and it has even less memory safety than C!

The elegance of it continues to impress though with functional programming to get the job done and compile time programming to mold the language into that DSL which expresses the problem perfectly.

An interesting project chose it as its lang: https://collapseos.org/

Tethered Forth programming on small devices is an underrated opportunity, IMO. There is also the opportunity to revise the OpenBoot project, I remember the days of automation for deployments at the Bios, it was an amazing tool for massive deployments of Sun T systems in telcos.

FORTH has been used to control deep space telescopes and planetariums --it's a great way to expose instrumentation for high-level access, but that access might not be human anymore, it could just as easily expose instrumentation to AI agents.

For example, a FORTH page could contain a prompt "Animate a galloping black and white zebra on the attached 64x32 RGB LED matrix, cache the code to do this on a FORTH page called ZEBRASHOW6432." Another could prompt "Run ZEBRASHOW6432 at the top of the hour during weekdays in the Pacific Time Zone." This might involve lifting C drivers from Arduino and CircuitPython for the 64x32 RGB LED matrix driver into FORTH (trivial) and building an MCP-to-FORTH server, but endless fun...

So I guess it's best to stop reading about FORTH and grab an rP0-2W and attach desired indicators, sensors, actuators and transceivers to see for yourself.