rupertl/eliza-ctss

The original ELIZA on an emulated CTSS environment

What it solves

This project allows users to compile and run Joseph Weizenbaum's original 1965 ELIZA code exactly as it was intended, using a reconstructed environment that mimics the hardware and software of the 1960s.

How it works

It uses the s709 IBM 7094 emulator to run the Compatible Time-Sharing System (CTSS). The project provides the necessary scripts and binaries to set up the CTSS environment, upload the transcribed SLIP library and ELIZA source code, and compile them within the emulated system. Users interact with the program via a telnet client.

Who it’s for

It is designed for computer historians, AI researchers interested in the origins of chatbots, and enthusiasts who want to experience one of the earliest examples of natural language processing in its original architectural context.

Highlights

  • Historical Accuracy: Runs the original 1965 code transcribed from physical printouts.
  • Full Emulation: Includes an IBM 7094 emulator and the CTSS operating system.
  • Reconstructed Library: Includes a reconstructed SLIP library to fill gaps in the original source printouts.
  • Multiple Setup Options: Offers both a manual quickstart and an automated Docker-based installation.

Related

  • Project
    liangdabiao/langgraph_multi-agent-rag-customer-support

    A multi-agent RAG customer support system built with LangGraph and LangChain that features security guardrails and a human-in-the-loop approval process for sensitive operations.

  • Project
    Rimagination/bili-note

    A tool that converts Bilibili videos and posts into structured Markdown notes by archiving subtitles, comments, and keyframes for use in personal knowledge bases.

  • Project
    CyberSunil/LLMVault

    LLMVault is a self‑hosted Flask app that offers 25 OWASP‑LLM security labs (Core, Advanced, Expert). Play Mode uses scripted bots for repeatable flags; Live Mode hooks a local LLM (e.g., Ollama) for unpredictable attacks. Features include a progress dashboard, Docker deployment, JSON‑based persistence, hints, and a “learn‑the‑fix” after each lab. Run with `pip install -r requirements.txt && python app.py` or via Docker. Intended for security training on LLM‑specific vulnerabilities.

  • Project
    SYuan03/Skill-Anything

    Skill‑Anything is a Python CLI that converts any source (PDF, video, web page, audio, or code repo) into a structured 12‑section study pack with notes, quizzes, flashcards, glossary, concept map, and optional AI‑agent skill export. It uses LLMs (configurable OpenAI‑compatible APIs) with a parallel map‑reduce pipeline, caching, and citation verification, and can output offline web sites, Anki decks, or `SKILL.md` bundles.