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
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...
Casibase is an open-source enterprise AI knowledge base platform supporting the Model Context Protocol and multiple AI models with features like admin UI, user management, and Single Sign-On.
Zotero MCP connects your Zotero research library with AI assistants like Claude via the Model Context Protocol, enabling advanced search, summaries, citation analysis, and PDF annotation extraction for enhanced research workflows.
MCP server enabling interaction with Obsidian via the Obsidian Local REST API community plugin, providing tools for file management, content retrieval, search, and content modification within Obsidian vaults.
Basic Memory is a knowledge management system that uses the Model Context Protocol to enable AI assistants to read and write structured knowledge stored locally in Markdown files, creating a persistent semantic graph for ongoing conversations and knowledge building.
ArXiv MCP Server is an MCP server that enables AI assistants to search, access, and analyze arXiv academic papers through a programmatic interface.
Trieve is an all-in-one infrastructure platform offering advanced search, recommendations, retrieval-augmented generation, and analytics via API with strong support for Model Context Protocol (MCP) integration.
The Microsoft Learn Docs MCP Server is a cloud-hosted service implementing the Model Context Protocol to provide AI assistants with real-time access to official Microsoft documentation through semantic search and standardized endpoints.
Grounded Docs MCP Server is an open-source, locally running MCP server that indexes and provides version-specific third-party documentation to AI coding assistants, improving accuracy and reducing hallucinations.
Supermemory MCP is a universal memory system that enables seamless access to personal memories across all large language models without requiring logins or paywalls.
MCP-Obsidian is a universal AI bridge for Obsidian vaults, enabling safe read/write access for any Model Context Protocol (MCP)-compatible AI assistant, preventing frontmatter corruption.
OpenContext is a personal context and knowledge store that integrates with existing AI coding agents to provide persistent memory, enabling smarter, context-aware interactions and seamless reuse of project knowledge across sessions and repositories.
Minima is an open-source on-premises RAG system that enables secure, private querying of local documents through conversational AI with integration support for ChatGPT and the Model Context Protocol (MCP).
mcp-knowledge-graph is an MCP server that provides persistent memory for AI models through a local knowledge graph, enabling user information retention across interactions and compatibility with any MCP-supporting AI platform.
MCP Tools for Obsidian is a plugin and local server that enable secure AI integrations with Obsidian vaults via the Model Context Protocol, providing semantic search, template execution, and controlled vault access for AI applications like Claude Desktop.
Context Portal MCP (ConPort) is a database-backed MCP server that builds a structured project-specific knowledge graph to enable AI assistants to provide context-aware, accurate responses through Retrieval Augmented Generation in development environments.
obsidian-mcp is an MCP server that enables AI assistants to interact with Obsidian vaults, providing tools for managing notes and tags through reading, creating, editing, and organizing content.
Memora is an MCP-compatible memory layer for AI agents, providing persistent, structured storage, semantic retrieval, and knowledge graph capabilities with cross-session context.
Obsidian MCP Server is a secure and efficient MCP server that enables large language models and AI agents to interact programmatically with Obsidian vaults for advanced knowledge base management and automation.
snexus/llm-search is an advanced Retrieval-Augmented Generation system that enables efficient querying and interaction with local document collections using customizable Large Language Models and supports integration via an MCP server.
mem0-mcp is an MCP server integrated with mem0 that manages coding preferences by providing tools to store, retrieve, and semantically search coding patterns and solutions through an SSE endpoint accessible by clients like Cursor.
Haiku SQLite RAG is a self-contained Retrieval-Augmented Generation library using SQLite that supports hybrid semantic and full-text search, multiple embedding and QA providers, and integrates with AI assistants via an MCP server.
An MCP server that enhances problem-solving by guiding sequential thinking and providing confidence-scored recommendations for MCP tool usage at each step.
The Anytype MCP Server is a Model Context Protocol server that enables AI assistants to interact with Anytype's API through natural language, facilitating seamless knowledge base management.
Kagi MCP server is an MCP server that integrates Kagi's search and summarization tools into MCP-compatible applications to enhance information retrieval and summarization capabilities.
TypeScript MCP server that connects AI assistants to Anki through AnkiConnect, exposing 42 tools for reviewing due cards, creating and editing notes, managing decks, tags, media, note types and study statistics.
ATLAS MCP Server is a Neo4j-based Model Context Protocol server designed to manage projects, tasks, and knowledge in LLM agent workflows using a three-tier architecture.
The graphrag-toolkit is a Python toolkit for building graph-enhanced Generative AI applications, featuring BYOKG-RAG for knowledge graph question answering and an MCP server for dynamic tool generation in multi-tenant environments.
MCP Apple Notes is an MCP server that enables semantic search and retrieval augmented generation over Apple Notes, allowing AI assistants like Claude to access and reference personal notes during conversations.
Ebook-MCP is an MCP server that enhances eBook interaction by enabling natural language conversations and AI-powered processing of EPUB and PDF formats.
The graphlit-mcp-server is an MCP Server for the Graphlit Platform that centralizes diverse data sources into a searchable, RAG-ready knowledge base for MCP clients, supporting extensive data ingestion, retrieval, and integration capabilities.
GPT Researcher MCP Server is an MCP protocol-based server that enables LLM applications to perform deep, validated, and comprehensive web research, enhancing information quality and reasoning capabilities.
MARM Systems is an official MCP server that provides a persistent, memory-powered collaboration layer for AI agents, enabling long-term recall, multi-agent coordination, and context sharing across platforms.
MemoryMesh is a knowledge graph server using the Model Context Protocol to provide structured memory persistence for AI models, especially suited for text-based RPGs and interactive storytelling.
MCP Documentation Server is a TypeScript-based MCP server providing local-first document management and AI-powered semantic search with Google Gemini AI integration for advanced document analysis and contextual understanding.
Python MCP server that gives LLMs live Wikipedia access, with search, full articles, summaries, sections, links and related topics across many languages and regional variants.
Strands Agents MCP Server is an MCP server that provides curated documentation access for Strands Agents to generative AI tools, enabling efficient search and retrieval of relevant information to facilitate AI agent development.
MCP server that gives AI agents persistent memory and task orchestration on a Neo4j knowledge graph, with local embeddings, semantic search and optional codebase file indexing.
Rust memory server for AI agents and robots exposing MCP, HTTP and ROS2 interfaces, with local embeddings, Hebbian reinforcement and decay so storage and recall need no LLM calls.
An MCP server implementation that enhances AI assistants by enabling semantic search and retrieval of documentation to augment responses with relevant context.
MoltBrain is a long-term memory layer for OpenClaw, MoltBook, and Claude Code agents that automatically learns and recalls project context using Model Context Protocol tools to enhance session continuity and productivity.
MCP server that drives Anki flashcard software through the AnkiConnect add-on, exposing tools and resources for decks, notes, tags, note types, search and AnkiWeb sync.
MCP server for a Paperless-NGX archive that exposes document listing, full-text search, upload, download and bulk editing plus tag, correspondent and document type management.
MCP Server for Deep Research is an MCP-based tool that transforms research questions into comprehensive, well-cited reports through a structured workflow involving question elaboration, subquestion generation, web search, content analysis, and report generation.
Unofficial MCP server for Bear Notes on macOS with relevance ranked search across titles, bodies and hierarchical tags, read only by default and an opt in edit mode that writes through the Bear URL handler.
TypeScript MCP server for managing GitHub Gists as personal knowledge, with tools for gists, files and comments plus optional daily notes, starring, archiving and reusable prompts.
mcp-simple-arxiv is an MCP server that enables large language models to search, retrieve, and read scientific papers from arXiv through their API, enhancing LLM capabilities with access to academic literature.
An MCP server implementation that connects to the Anki desktop app, enabling programmatic card review and creation through the Model Context Protocol.
An MCP server that searches local Claude Code conversation history, with search across eleven scopes (conversations, files, errors, plans, config, tools, memories) and a session inspection tool.
Token-efficient Notion MCP server exposing 43 operations behind two tools, with personal access token authentication, batched mutations, idempotency keys and full markdown round-trip for headless agent use.
Small TypeScript MCP server for Zotero that lets an AI client browse collections, inspect item details, search the library and list recently added papers through the Zotero web API.
Python MCP server implementing the Zettelkasten method, letting MCP clients create atomic Markdown notes, link them with typed semantic relations and search the resulting knowledge graph.
Python MCP server that exposes a Zotero reference library to AI assistants through three tools for searching items, reading full item metadata and extracting attachment full text.
Go shared-memory server for multi-agent systems combining PostgreSQL with pgvector and a Neo4j knowledge graph, exposing its session API to agents through a built-in MCP server.
An MCP server for Outline document management with tools for searching, reading, creating and editing documents, managing collections, threaded comments and backlinks.
An MCP server that fetches the LaTeX source of an arXiv paper instead of its PDF, so equation-heavy content reaches the model as markup rather than extracted text.
Self-hosted Next.js site search that crawls a website into pgvector, generates llms.txt, and ships an MCP server package so Claude Desktop and Cursor can query the indexed documentation.
Local Python MCP server that runs RAG-style web search across nine search backends, ranks results with on-device MediaPipe embeddings and returns extracted page text, requiring no API keys.
Python MCP server that reads the local Apple Notes SQLite database on macOS so Claude Desktop can list, read and search notes; read-only, with no support for encrypted notes or attachments.
An MCP server that connects LLM clients to any MediaWiki instance, with tools for reading, comparing, searching and editing pages across multiple configured wikis.
An MCP server that gives agentic systems web search through a self-hosted SearXNG instance.
An MCP server wrapping the Brave Search API with tools for web, image, video, news, local points-of-interest and full-page context search.
An MCP server for Notion that searches a workspace and reads, creates and updates pages, blocks, comments and databases with markdown conversion.
Cloudflare Workers MCP server that indexes your GitHub starred repositories and their READMEs into R2 and AutoRAG, then exposes one natural-language search tool over them.
An MCP server for the Naver Open API, exposing search across blogs, news, books, images and other Naver services.
MCP server for the Vectorize platform that exposes vector retrieval over a configured pipeline, extraction of any document into chunked Markdown, and private deep research reports with optional web search.
An MCP server for Needle that stores and organises documents into collections and answers semantic searches over them, giving a model persistent retrieval.
A community MCP server for Box enterprise content, covering file and folder operations, search and document text extraction. It is discontinued in favour of Box's hosted server.
Python MCP server for Google Keep built on gkeepapi, with tools to search, read, create and update notes and checklists, set colour, pin, archive and trash state, and manage labels, collaborators and media.
A Node.js MCP server that wraps the Mem0 platform to give LLM agents persistent memory, with tools to add, search, list, update, delete, export and rate memories across cloud, Supabase or local storage.
TypeScript MCP server for the Open Library API that lets AI assistants search books and authors, fetch author details and resolve cover and author photo image URLs.
An MCP server providing web search through OpenAI's reasoning models, with configurable reasoning effort and location-based result customisation.
An MCP server exposing a single retrieve tool that queries a Ragie knowledge base. Ragie now supports MCP natively, so this wrapper is no longer needed.
MCP server providing a persistent memory and knowledge-graph store for LLMs, powered by libSQL, with entity and relation management and relevance-ranked fuzzy text search.
Archived TypeScript MCP server that turns each LlamaCloud managed index named on the command line into its own query tool, so a client sees separately described retrieval tools with per-index result limits.
A TypeScript MCP server providing DuckDuckGo web search with configurable result count and safe-search level, returning formatted markdown.
A Python MCP server for the Wolfram Alpha API for mathematical, scientific and data queries, shipping an example MCP client using Gemini through LangChain and a Gradio interface.
An MCP server for the Naver Search and DataLab APIs, covering web, news, blog and shopping search plus search-trend and shopping-insight analysis.
Python MCP server for Apple Books that exposes collections, books, reading status, chapter text and annotations as tools, plus an opt-in write mode that edits user-created collections directly in the library database.
MCP server for Agentset, an open-source Retrieval-Augmented Generation platform, exposing namespace-scoped document retrieval to MCP clients through an npx-launched Node package.
Python MCP server wrapping the Papers with Code API with tools to search papers, authors, datasets, conferences and research areas, and to extract readable text from a paper URL.