M3-Agent: a multimodal intelligence with long-term memory and capable of processing audio and video
M3-Agent is a multimodal intelligent body framework developed by the ByteDance SEED team. Its core feature is a long-term memory capability, capable of building and constantly updating its memory by processing real-time video (watching) and audio (listening) inputs, just like humans. This memory system doesn't just record what happened (situational memory), but can also be used from...
DiffMem: a Git-based versioned memory repository for AI intelligences
DiffMem is a lightweight memory backend designed for AI intelligences and conversational systems. It innovatively uses Git as the core of the memory store, saving AI memories as human-readable Markdown files. Git's commit history is used to track the evolution of memories over time, while the system employs an in-memory BM25 index to...
Clueoai: Injecting consistent personality traits and long-term memory into a large language model
Clueoai is a personification infrastructure designed for Large Language Models (LLMs). It provides a simple Application Programming Interface (API) that developers can call to infuse their AI applications with stable and consistent personality traits. This service aims to address the problem of response monotony and lack of personality in traditional AI interactions. Through...
ComoRAG: a cognitive memory retrieval tool for long narrative reasoning
ComoRAG is a Retrieval Augmented Generation (RAG) system designed to address long documents and multi-document narrative comprehension. Traditional RAG methods often encounter difficulties when dealing with long stories or novels due to complex plots and evolving character relationships. This is due to the fact that most of them utilize a stateless, one-shot retrieval approach, which makes it difficult to capture long up and down...
memU: an open-source framework for creating long-term memories for AI companions
memU is an open source memory framework designed for AI companions. While current big language models generally have short memories and are unable to establish long-term connections with users, memU acts like an intelligent “memory folder” for AI, allowing AI to remember users' identities, preferences, and past conversations, and to interact with them on a continuous basis with...
Persistent AI Memory: Persistent Local Memory Storage for AI Assistants
Persistent AI Memory is an open source project designed to provide persistent local memory storage for AI assistants, language models (LLMs) and Copilot in VS Code. It stores dialog, memory, and tool invocation records via an SQLite database and supports semantic search and real-time file monitoring. The system ...
ByteRover: a management tool to enhance the memory of AI coding assistants
ByteRover is a memory management tool for AI coding assistants designed to help developers store, share and reuse coding experiences. It records the interactions and contexts of AI assistants during the coding process through a shared memory layer, allowing AI assistants to continuously learn and avoid repeating mistakes.ByteRover supports working with a wide range of AI development environments (...
Cursor Memories: Provides persistent context memory for Cursors.
Cursor Memories is an open source project, hosted on GitHub, that aims to provide persistent context memory capabilities for the AI code editor Cursor. It helps AI assistants retain project information across sessions through structured document files, solving the problem of AI forgetting the context after each session...
Convo: Logging and Debugging Tools for Building Intelligent AI Agents
Convo is a tooling platform focused on AI agent development that helps developers quickly build, debug and optimize LangGraph-based intelligent agents. It provides logging, state management, and multi-user memory capabilities through simple code integration, reducing the developer's burden of database configuration and infrastructure management.Convo ...
Cipher: an open source memory layer MCP tool for coding assistants
Cipher is an open source memory layer tool designed for coding assistants. It seamlessly integrates with a wide range of programming tools and artificial intelligence assistants such as Claude Code, Cursor and Windsurf via the Model Context Protocol (MCP) protocol.Ciphe...
MIRIX: A Multi-Intelligent Personal Assistant for Intelligent Tracking of Screen Activity
MIRIX is an innovative multi-intelligent personal assistant focused on tracking user screen activities and providing intelligent Q&A services. It builds a searchable timeline of a user's digital life by capturing real-time visual data and transforming the user's digital actions into structured memories.MIRIX combines core memory, situational memory, semantic memory, procedural memory, resource memory...
Passage of Time MCP: A Service Providing Time-Awareness and Computational Capabilities for Language Modeling
Passage of Time MCP is an open source Model Context Protocol (MCP) server project designed to provide time-awareness and time-computation capabilities for Large Language Models (LLMs). The project was developed by Jérémie Lumbroso and Claude O...
Core: a tool for personalized memory storage for large models
Core is an open source tool developed by RedPlanetHQ to provide personalized memory storage capabilities for large models (LLMs). With Core, users can build and manage their own memory maps, saving text, conversations, or other data to a private knowledge base. The tool supports storing records of user interactions with the Large Model...
Portia AI: A Python Toolkit for Building Intelligent Automated Workflows
Portia AI is an open source Python software development kit (SDK) focused on helping developers build intelligent, automated workflows. It enables users to easily design and run complex task processes through a multi-intelligence system.Portia AI supports developers to customize their workflows, provides reliable production environment support...
MemOS: An Open Source System for Enhancing the Memory Capacity of Large Language Models
MemOS is an open source system focused on providing memory enhancements for Large Language Models (LLMs). It helps models better store, retrieve, and utilize contextual information through innovative memory management and scheduling mechanisms.MemOS excels in tasks such as multi-hop inference, open-domain Q&A, and temporal inference, improving performance significantly compared to traditional models, exemplified...
Praxos: building a reliable structured knowledge base for AI intelligences
Praxos.ai is a kernel designed for AI Agents. It provides a development environment designed to address common challenges in building AI Intelligents, such as context management confusion, complex cue engineering, and system runtime failures. The core of Praxos works by taking raw data from various sources,...
Muscle-Mem
Muscle-Mem is an open source Python tool hosted on GitHub and developed by pig-dot-dev. It is designed to provide behavioral caching capabilities for AI agents to help reduce large language model (LLM) calls in repetitive tasks, thereby increasing runtime speed, reducing variability, and saving costs....
Mem0: an open source project that provides an intelligent memory layer for AI assistants and agents
Mem0 (pronounced “mem-zero”) is an open source project that provides an intelligent memory layer for AI assistants and agents. It remembers user preferences, adapts to individual needs, and improves over time, making it ideal for customers supporting chatbots, AI assistants, and autonomous systems.Mem0 manages and retrieves through a hybrid database approach...
PhiData: Building AI Intelligence with Memory, Knowledge and Tools
PhiData is a framework designed for developing intelligent AI assistants. It enables AI assistants to conduct long-term conversations, provide accurate business context, and perform various operations through enhanced memory, knowledge integration, and tool invocation capabilities.PhiData not only enhances the intelligence of AI assistants, but also extends their application scope, enabling them to be more precise...
Top
