Popular GitHub Repositories for Physical Memory

For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.

A high-throughput and memory-efficient inference and serving engine for LLMs

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! ?

The Memory layer for AI Agents

Agno is a lightweight library for building Multimodal Agents. It exposes LLMs as a unified API and gives them superpowers like memory, knowledge, tools and reasoning.

Letta (formerly MemGPT) is the stateful agents framework with memory, reasoning, and context management.

Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.

Alluxio, data orchestration for analytics and machine learning in the cloud

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

Numenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strictly on the neuroscience of the neocortex.

Reliable LLM Memory for AI Applications and AI Agents

Serverless AI Workflows for Data & ML Teams

? Refly is an open-source AI-native creation engine. Its intuitive free-form canvas interface combines multi-threaded dialogues, artifact, AI knowledge base integration, chrome extension clip & save, contextual memory, intelligent search, WYSIWYG AI editor and more, empowering you to effortlessly transform ideas into production-ready content.

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.

Zep | The Memory Foundation For Your AI Stack

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.

C++ DataFrame for statistical, Financial, and ML analysis -- in modern C++ using native types and contiguous memory storage

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.