MemPalace/mempalace
MemPalace is an open-source, local-first AI memory system that stores and retrieves conversation history verbatim using semantic search, supporting pluggable backends like ChromaDB and integrating ...
Awesome MCP › Knowledge & Memory
GreatScottyMac/context-portal
Context Portal MCP (ConPort) is a specialized Model Context Protocol (MCP) server designed to serve as a structured memory bank for software projects. It builds a project-specific knowledge graph that captures and organizes critical project information such as decisions, progress, architectural patterns, and custom data like glossaries or specifications. This structured context is stored in a database backend (SQLite) with one database per workspace, enabling efficient management, searching, and updating of project context compared to traditional file-based memory systems. ConPort is designed to be integrated with AI assistants and developer tools within IDEs and other interfaces, providing them with enhanced context awareness. By leveraging vector embeddings and semantic search capabilities, it supports Retrieval Augmented Generation (RAG), allowing AI to generate more accurate and contextually relevant responses based on the up-to-date project knowledge graph. This makes it an ideal backend for AI-driven development environments where precise and dynamic project context is crucial. The server is implemented in Python using FastAPI and offers a comprehensive suite of MCP tools for interaction. It supports multi-workspace management through explicit workspace IDs and primarily operates in STDIO mode for tight integration with IDEs. The system also includes features like database schema evolution management via Alembic migrations, ensuring data integrity and seamless updates. Installation is streamlined using the 'uv' environment and package manager, with recommended deployment via 'uvx' to simplify environment handling. The server requires Python 3.8 or higher and is compatible with various MCP clients that can provide the necessary workspace context. Overall, Context Portal MCP enhances AI assistant capabilities by providing a robust, queryable, and semantically rich project memory, facilitating smarter and more context-aware software development workflows.
https://github.com/GreatScottyMac/context-portal
Also in Knowledge & Memory
siyuan-note/siyuan
SiYuan is a privacy-first, self-hosted personal knowledge management system featuring block-level referencing, Markdown WYSIWYG editing, and support for the Model Context Protocol (MCP).
topoteretes/cognee
Cognee is an open-source project that provides scalable and modular memory capabilities for AI agents using ECL pipelines, enabling efficient management and retrieval of past interactions and diverse data types.
vectorize-io/hindsight
Hindsight is an agent memory system designed to create smarter, learning AI agents by moving beyond simple conversation history recall to encompass a biomimetic storage architecture for long-term m...
screenpipe/screenpipe
Screenpipe is a local-first, AI-powered memory tool that records computer activity (screen, audio, accessibility tree) to provide a searchable, automated context for personal AI agents and users, i...
Olow304/memvid
Memvid is a video-based AI memory library that stores millions of text chunks in MP4 files with ultra-fast semantic search, eliminating the need for traditional databases and enabling portable, efficient AI memory management.
EverMind-AI/EverOS
EverOS is an open-source Python framework for self-evolving, portable, long-term memory for AI agents, supporting multimodal ingestion and local-first persistence with Markdown as the source of truth.
MemTensor/MemOS
MemOS is a Memory Operating System for LLMs and AI agents that unifies long-term memory management, offering a single API for structured, multi-modal memory with enterprise-grade optimizations, sig...