"memory" matching MCP servers:

A local MCP server that helps you maintain a personal Japanese learning knowledge base, including vocabulary, confusion relations, mistakes, and spaced-repetition reviews. It provides tools and prompts for managing and reviewing your Japanese learning data without calling external LLM APIs.

An interactive flashcard MCP App for Claude Desktop. Claude generates flashcards from your request or the conversation and renders them as an inline, gradeable flip-card review with spaced repetition.

A technical interviewer that ingests GitHub repos, teaches you your own code, and conducts mock interviews with persistent memory of your weak spots.

A shared memory MCP server for the Senegalese MOHEBS teaching and learning materials pipeline that ensures AI-generated documents remain consistent in characters, terminology, and concept coverage while varying example domains, operating across grade and subject via Firebase storage.

A runnable MCP server for learning GH-600 domain 2.0, providing four example tools (repo info, issues, summaries, safe file read) and a resource, using deterministic in-memory data.

Enables humans and AI agents to collaborate live on documents in a browser-based editor, with agents connecting via OAuth-enabled MCP tools for writing, commenting, memory, files, web retrieval, and backups. It can optionally integrate school drive and learning-platform access.

MCP server for the Recall LeetCode memory engine. Enables logging problems and reviews directly from tutoring sessions, plus retrieving due reviews and stats.

Enables an AI assistant to act as the memory of a personal English-learning app: read progress and words due for review, run short practice conversations, and store sentences, corrections, new words, rubric scores, and checked exercises back to the user's dashboard. Also lets the assistant grow the flashcard deck and adjust word familiarity, which reschedules spaced-repetition reviews.

Enables users to fetch ready-made Obsidian vault settings and note templates, and to audit Markdown notes for broken wikilinks, unlinked notes, missing definitions or examples, and lectures that omit their concepts. All tools are read-only and note content is processed in memory for a single request and discarded.

Provides Claude with persistent memory about the user's skills, learning history, and project context to deliver personalized, adaptive explanations and avoid repeating basics.

Gives Claude persistent memory to coach language learning: it stores a personal profile, builds weekly plans and daily lesson tasks, schedules spaced-repetition review cards, and tracks streaks and XP. All data is kept in a single local JSON file with no API key, account, or network calls.

Provides personalized CSS learning updates by tracking known concepts in memory, fetching latest CSS news via Perplexity, and guiding users through new CSS features they haven't learned yet.

An MCP server that wraps the Bobbin Apple II emulator, providing tools for memory access, screen reading, BASIC program execution, and disk image management to enable autonomous experimentation with Apple II control techniques.

Enables AI clients to fetch public chessvox.com chess data — the daily puzzle for any past day, batches of 20 mate-in-1 training puzzles, and starter opening repertoires with UCI preview lines — over read-only, key-free requests. Results are cached in memory and returned as structured FEN/UCI payloads, so assistants can quiz tactics or walk through openings without an account.

MCP server for StudioMeyer Academy that connects Claude Code, Cursor, or Claude Desktop to track learning progress in the Memory-First AI Operator curriculum. It enables users to view lessons, complete quizzes, earn certificates, and run spaced-repetition reviews directly in chat.

Enables an assistant to retrieve Quranic verses in Uthmani Arabic with any of hundreds of translations, look up and search ten major hadith collections, and compute prayer times offline from the sun's position. Every quotation comes back with its exact reference so answers can be verified rather than paraphrased from memory.

Enables Claude Code and Cowork to act as a personal coach grounded in a locally indexed library of YouTube talks, websites and PDF books, answering with exact-second, paragraph or page citations and recalling the user's goals and decisions per Project. Search, memory and the usage log run on the user's own machine, and changing Sources rebuilds the knowledge base without any fine-tuning.