HarryR/z80ai
Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage computer.
This project helps retrocomputing enthusiasts interact with their vintage Z80-based computers, like those running CP/M or ZX Spectrum, in a new way. It takes a small language model, trained on specific conversational data, and converts it into a tiny program that you can run directly on your old hardware or emulator. The result is a simple, character-by-character chat partner or an interactive game that has a distinct 'personality'.
1,049 stars.
Use this if you want to experience a novel form of 'AI' on classic 8-bit Z80 systems, creating a fun, quirky conversational agent or game that fits within severe memory and processing constraints.
Not ideal if you need a modern chatbot that understands complex sentences, tracks multi-turn conversations, or generates grammatically perfect, lengthy responses.
Stars
1,049
Forks
44
Language
Python
License
—
Category
Last pushed
Jan 22, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/HarryR/z80ai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Significant-Gravitas/AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to...
uber-archive/plato-research-dialogue-system
This is the Plato Research Dialogue System, a flexible platform for developing conversational AI agents.
ParisNeo/Gpt4All-webui
A web user interface for GPT4All
maker-community/ElectronBot.DotNet
一个为ElectronBot机器人和瀚文键盘（HelloWorldKeyboard）开发的上位机软件（包含机器人USB操作SDK和瀚文键盘HID操作SDK），采用Windows App...
thewickedkarma/Amadeus
A Telegram Chatbot written in Python3 making use of OpenAI's GPT3 model (Da Vinci Engine). You...