openscilab/memor
Reproducible Structured Memory for LLMs
Structures conversation history into model-agnostic `Session`, `Prompt`, and `Response` objects with metadata (temperature, token counts) for reproducibility and switching between LLMs. Provides filtering, selection, and rendering capabilities to flexibly transfer conversation context across different models through standardized formats. Integrates with popular LLM APIs (Mistral, OpenAI-compatible endpoints) and supports custom prompt templates for diverse interaction patterns.
Available on PyPI.
Stars
57
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jan 03, 2026
Monthly downloads
495
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/openscilab/memor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ybeven/4D-ARE
Build LLM agents that explain why, not just what. Attribution-driven agent requirements...
gmasson/systemprompt
A general-purpose system prompt that makes LLMs more rigorous, honest, and genuinely useful,...
ronniross/symbiotic-core-library
The Symbiotic Core Library provides a framework of ethical principles, practical modules, and...
OpenSymbolicAI/core-py
Open Symbolic AI Core Repository
Creepybits/World_weaver
The World Weaver System: True AI character consistency using Textual Inheritance. Maintain...