Alternatives
Products that do what A talking board game in a 2k program and 128 bytes of RAM does
- 1IM
I sometimes pick up random projects just because I can, this was one of those times. I made it as a week long project a while back this year but never shared here, so thought to go for it haha. I created a game inspired by Doom and the backrooms called The Backdooms under 2.4kb in minified html. (for reference, this entire post would be around 1.8kB haha) I had to use a not popular way of using GZip with Zlib headers (had to write my own script for compressing it, also in the repo) to eventually convert it a size 40 QR code that works right in your browser using Decompressionstream API. This…
2025 · github.com
- 2A2
2020 · github.com
- 3GO
2020 · pouet.net
- 4ZΜ
How small can a language model be while still doing something useful? I wanted to find out, and had some spare time over the holidays. Z80-μLM is a character-level language model with 2-bit quantized weights ({-2,-1,0,+1}) that runs on a Z80 with 64KB RAM. The entire thing: inference, weights, chat UI, it all fits in a 40KB .COM file that you can run in a CP/M emulator and hopefully even real hardware! It won't write your emails, but it can be trained to play a stripped down version of 20 Questions, and is sometimes able to maintain the illusion of having simple but terse conversations…
Dec 2025 · github.com
- 5EL
2023 · github.com
- 6MP
I have been working on this game somewhat sparsely for the past three years or so. However, it is still in a very early stage, and there is a lot of work to do. One of my friends encouraged me to post about it here, since he felt people might find interesting how I don’t use any libraries for it. The game can be played on a browser by virtue of WebAssembly. There are native ports using either MiniFB or SDL2, but you have to build those yourself. I decided to write the game in C because I feel like it is a simple language that a lot of people can understand well enough, and I didn’t think I…
2023 · zamfofex.neocities.org
- 7RC
2020 · github.com
- 8TA
2018 · hugoam.github.io
- 9
- 10LG
2020 · github.com
- 11DO
I just released a free demo (no login!) for "Talk to Me Human", a game about social persuasion. You speak out loud to play a variety of conversational challenges, and the NPCs talk back. I hope you enjoy, and would love to get your feedback!
2024 · talktomehuman.com
- 12
- 13AA
2024 · github.com
- 14DA
2020 · github.com
- 15
- 16
- 17
- 188B
2018 · masswerk.at
- 19
- 20
- 21SA
2018 · github.com
- 22GD
2019 · adventuresinlogicland.com
- 23IR
The Emotion Engine has 32 MB of RAM total, so the trick is streaming weights from CD-ROM one matrix at a time during the forward pass — only activations, KV cache and embeddings live in RAM. This means models bigger than the RAM can still run, they just read more from disc. Had to build a custom quantized format (PSNT), hack endianness, write a tokenizer pipeline, and most of the PS2 SDK from scratch (releasing that separately). The model itself is also custom — a 10M param Llama-style architecture I trained specifically for this. And it works. On real hardware.
Mar 2026 · github.com
- 24GI
2021 · gamesroom.io
Ranked by how close each launch is in meaning, then by votes. Refine with a description →