Universal memory layer for AI Agents
-
Updated
Nov 27, 2025 - Python
Universal memory layer for AI Agents
OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend.
Build memory-native AI agents with Memory OS — an open-source framework for long-term memory, retrieval, and adaptive learning in large language models. Agent Memory | Memory System | Memory Management | Memory MCP | MCP System | LLM Memory | Agents Memory System |
Profile-Based Long-Term Memory for AI Applications. Memobase handles user profiles, memory events, and evolving context — perfect for chatbots, companions, tutors, customer service bots, and all chat-based agents.
Add long-term memory to any AI in one line. Self-hosted, open, and framework-free.
📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥
Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch
[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.
Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".
LightMem: Lightweight and Efficient Memory-Augmented Generation
A completely private, locally-operated Ai Assistant/Chatbot/Sub-Agent Framework with realistic Long Term Memory and thought formation using Open Source LLMs. Qdrant is used for the Vector DB.
PowerMem: Your AI-Powered Long-Term Memory — Accurate, Agile, Affordable.
solving long term memory storage for llms
A library for benchmarking the Long Term Memory and Continual learning capabilities of LLM based agents. With all the tests and code you need to evaluate your own agents. See more in the blogpost:
MyShelf is an experiment to create a GenAI utility to track reminders, memories, random adhoc information, shopping lists, and more.
HaluMem is the first operation level hallucination evaluation benchmark tailored to agent memory systems.
The ChatGPT Long Term Memory package is a powerful tool designed to empower your projects with the ability to handle a large number of simultaneous users and external sources.
A smart AI voice assistant with multi-language support and long-term memory. Currently best for Swedish and English. Compatible with Windows and Raspberry Pi. The assistant can use various functions and tools to answer questions (Google, Wolfram Alpha, etc.). Based on OpenAI's GPT-models, Google STT and TTS, and ElevenLabs TTS.
Curse-of-memory phenomenon of RNNs in sequence modelling
Add a description, image, and links to the long-term-memory topic page so that developers can more easily learn about it.
To associate your repository with the long-term-memory topic, visit your repo's landing page and select "manage topics."