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
mcp-memory-libsql is a Model Context Protocol server that gives language models a persistent memory system backed by libSQL. Written in TypeScript, it implements the standard MCP memory interface as a knowledge graph of entities, observations and relations, so an assistant can store facts across sessions and recall them later. Entities can be created and updated with observations, deleted, searched by text, and explored through their relationships, while relations between entities can be created, deleted and queried. The server's text search is optimized for LLM context efficiency: it uses fuzzy matching and ranks results by relevance, weighting name matches above type matches above observation matches, so the most pertinent memories surface first without flooding the context window. Storage uses a libSQL database with separate tables for entities, observations and relations, each carrying timestamps. It works with both local SQLite files and remote libSQL databases such as Turso, selected through the LIBSQL_URL environment variable, with secure token-based authentication for remote instances via LIBSQL_AUTH_TOKEN; if no URL is provided it defaults to a local file. Configuration examples are given for Cline and for Claude Desktop under WSL, and the server is typically launched through npx. It is aimed at developers who want to give AI assistants durable, queryable long-term memory and a knowledge graph that persists locally or in the cloud.
https://github.com/spences10/mcp-memory-libsql
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 ...
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).
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.
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 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...
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.
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.
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...