CLI tool for GPT models with long-term memory (no longer maintained)
Top 81.8% on sourcepulse
This project provides a C++ command-line interface (CLI) for interacting with OpenAI's GPT models, offering long-term memory via embeddings and custom document Q&A. It targets users who prefer a terminal-based experience over web GUIs and seek enhanced memory capabilities beyond the standard context window.
How It Works
The bot leverages embeddings to store and retrieve conversation history and custom documents, effectively creating a near-infinite memory capacity limited only by disk space. It streams responses token-by-token, mimicking the ChatGPT web experience, and supports features like chat history saving/loading, custom initial prompts, and undo/reset commands.
Quick Start & Requirements
GPT3Bot.exe
or run.bat
for Windows, or ./GPT3Bot
for Linux/macOS.Highlighted Details
Maintenance & Community
The project is explicitly marked as "NO LONGER MAINTAINED." The author cites advancements in LLM context windows and integrated RAG as reasons for discontinuation, recommending alternative GUIs like SillyTavern and LobeChat.
Licensing & Compatibility
The README does not specify a license. Compatibility for commercial use or closed-source linking is not addressed.
Limitations & Caveats
The project is no longer maintained, meaning no future updates or bug fixes are expected. The author suggests that direct higher context windows in newer LLMs are now preferable to embedding-based memory solutions. The system proxy feature is Windows-only due to compilation issues on other OS.
1 year ago
1 day