Show HN: Project Wisteria-A BYOK chatbot that saves thoughts and memory locally

Category: ai-ml

Tags: llm, memory-management, byok, chatbot, context-window

Score: 4.3/10 (Innovation: 5, Technical: 5, Documentation: 3, Utility: 4)

Wisteria is a BYOK chatbot client that implements a custom hierarchical memory architecture for long-term LLM conversations, with features like thought records and photo memory. It aims to prevent context window saturation and reduce memory loss through compression techniques, but the project is early-stage with minimal documentation and no public code or license.

Target audience: AI enthusiasts and developers interested in LLM memory systems

Repository: https://negativeabsence.com/wisteria/

View on Hacker News