Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured memories, Mirix transforms raw inputs into a rich knowledge base that adapts to your digital experiences.

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 |

User Profile-Based Long-Term Memory for AI Chatbot Applications.

Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory and recall to any model in minutes.

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

[COLM 2025] Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale

HaluMem is the first operation level hallucination evaluation benchmark tailored to agent memory systems.

Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design. Awesome-AI-Memory 是一个 集中式、持续演进的 AI 记忆知识库，系统性整理了与 大模型记忆（LLM Memory）与智能体记忆（Agent Memory） 相关的前沿研究、工程框架、系统设计、评测基准与真实应用实践。

✨ mem0 MCP Server: A memory system using mem0 for AI applications with model context protocl (MCP) integration. Enables long-term memory for AI agents as a drop-in MCP server.

Reproducible Structured Memory for LLMs

Reliable and Efficient Semantic Prompt Caching with vCache

Universal infinite memory layer for Developer AI assistants. One shared brain across Claude, Cursor, Windsurf & more. 100% local, built on MCP standard. Stop re-explaining context

A MCP (Model Context Protocol) server providing long-term memory for LLMs

A simple MCP server that stores and retrieves memories from multiple LLMs.

Official Python SDK for SwastikAI

Code and data for VTCBench, a vision-text compression benchmark for Vision Language Models.

a human-like, self-evolving, self-cleaned AI memory system for LLM

A collection of intelligent AI agents built using Ollama, LangChain, and local LLMs — including chatbots, voice assistants, web scrapers, document readers, and custom tools. No APIs required. Fully offline.

[EMNLP 2025 Main] LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models

Portable_TA is a lightweight, OpenAI-compatible LLM service that acts as an always-available AI Teaching Assistant. It provides document-grounded answers using RAG, maintains conversation memory, and integrates easily with tools like OpenWebUI for fast, portable, and intelligent student support.