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
needle-ai/needle-mcp
Needle MCP Server connects MCP clients to Needle, a hosted retrieval-augmented generation service. Its tools cover both sides of a retrieval workflow. On the write side, documents are added to named collections, so material accumulates across sessions instead of being pasted into a context window and forgotten when the conversation ends. On the read side, semantic search runs over a collection and returns the passages relevant to a query, with the embedding, chunking and index maintenance handled by Needle rather than by the user. Collection management tools let a model create and list collections, which is how separate bodies of material — one project's documentation, one client's contracts — stay separated rather than blending into a single index that returns confusing matches. The practical effect is long-term memory for an assistant: a document indexed weeks ago is retrievable now. It is a Python project, installable through Smithery for Claude Desktop, and requires a Needle API key. Because indexing and storage happen on Needle's infrastructure, the trade-off is the usual hosted one — no local vector database to run, in exchange for documents leaving the machine. The audience is people who want a durable searchable document store behind their assistant without operating retrieval infrastructure themselves.
https://github.com/needle-ai/needle-mcp
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...