The Memory layer for your AI apps

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.

Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

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.

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:

Augment AI agents with long-term memory through knowledge graph 🧠

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.

A CLI for improve your memory

Get started integration Llama Index into your swarms application now!

Testing code and demo episodic information for the ROS ltm package.

chatbot Ai with long-term memory and additional inputs

Code for NeurIPS paper: https://openreview.net/forum?id=5wdvW_hI7bP

Long Term Memory for robots using ROS. Thesis project.

Obesity impairs cognitive function with no effects on anxiety-like behaviour in zebrafish

Warmup initialisation procedure for RNNs

Example code for a basic Long Term Memory Chatbot using Qdrant and a conversation history list.

Research Implementation of paper "Augmenting Language Models with Long-Term Memory".

PyTorch implementation of the (neuromodulated) bistable recurrent cell