Awesome GitHub RepositoriesAgent Memory Systems

MemGPT is a memory management framework and external memory layer for large language models. It functions as a platform for building stateful AI agents that maintain a persistent identity and continuous context across multiple sessions. The system enables agents to bypass fixed context window limitations by using a virtual context windowing approach. This allows models to manage their own memory through internal commands to search, update, and delete stored information within a hierarchical structure of short-term working context and long-term archival storage. The framework provides a local

Agent-S is a multimodal AI agent and LLM desktop automation framework designed to control operating systems through graphical user interface interactions. It functions as a computer use interface, utilizing vision-language grounding to translate natural language goals into precise screen coordinates and system actions. The project differentiates itself by combining structured accessibility tree inspection with vision-based element localization. It manages cross-application workflows by mapping conceptual descriptions to physical pixels and simulating low-level keyboard and mouse events to mov

NeurIPS'24 HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG Knowledge Graphs Personalized PageRank.

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

[Website](https://os-copilot.github.io/) [Arxiv](https://arxiv.org/abs/2402.07456) [PDF](https://arxiv.org/pdf/2402.07456.pdf) [Documentation](https://os-copilot.readthedocs.io/en/latest/)

The Tradememory Protocol is a persistent, multi-layered memory and audit framework designed for artificial intelligence trading agents. It provides a structured architecture for agents to maintain episodic, semantic, and procedural knowledge across trading sessions, ensuring that decision-making is informed by long-term recall and historical context. The framework distinguishes itself through a combination of cryptographic integrity and cognitive modeling. It employs a tamper-evident logging system that uses hashed sequences to verify the history of trading decisions, alongside an outcome-wei

Read this in Chinese (阅读中文版本).

User Behavior Simulation with Large Language Model based Agents

Welcome to the codebase for our paper, "Language Models can Solve Computer Tasks". In this codebase, you will find the implementation of our RCI agent, which uses a pre-trained language model to execute computer tasks in MiniWoB++ benchmark guided by natural language. The agent employs a simple…

AriGraph functions as the external memory architecture for large language models (LLMs), featuring a knowledge graph that is built from the ground up. This memory, configured as a semantic knowledge graph with added episodic vertices and edges, greatly improves the performance of…

This repo provides the PyTorch source code of our paper: VideoAgent: Long-form Video Understanding with Large Language Model as Agent (ECCV 2024). Check out project page here!

WorldGPT: Empowering LLM as Multimodal World Model

HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model

This is the official code implementation of paper From Commands to Prompts: LLM-based Semantic File System for AIOS.

Sen Li, Ruochen Wang, Cho-Jui Hsieh, Minhao Cheng, Tianyi Zhou

This repository contains the main CALYPSO system from the paper CALYPSO: LLMs as Dungeon Masters’ Assistants. CALYPSO takes the form of a Discord bot that DMs can use to understand D&D monsters and brainstorm encounter ideas.

To get started, clone the KARMA repository: ` git clone https://github.com/WZX0Swarm0Robotics/KARMA `