Awesome MCPKnowledge & Memory

feuerdev/keep-mcp

⭐ 100 Python added to this list on 2025-05-14 repository created 2025-03-31

keep-mcp is a Model Context Protocol server for Google Keep, distributed so a client can run it with pipx or uvx and configure it with two environment variables, GOOGLE_EMAIL and GOOGLE_MASTER_TOKEN. It builds on gkeepapi, which talks to Keep through an unofficial private API, so it needs a Google master token rather than an ordinary password. The README is clear that such a token has full access to the account and should be treated like a password, and it points to the browser-assisted exchange documented by gpsoauth, runnable either as local Python or in Docker; it explicitly warns against the older perform_master_login flow, which is unreliable and often returns a BadAuthentication error. The tool set is broad. Query tools find notes case-insensitively with filters for labels, colours, pinned, archived and trashed state, creation and update date ranges in ISO 8601 UTC, and a result limit, while another tool fetches a single note by identifier. Creation and update tools add notes and checklists, edit title and text, and add, update or delete checklist items. State tools set a note colour from a fixed palette, pin, archive, trash, restore and mark notes for deletion. Further tools list, create and delete labels and attach or detach them from notes, list, add and remove collaborator email addresses, and list a note's media blobs with their links. A safety default limits every destructive or modifying operation to notes the server itself created, identified by an automatically applied keep-mcp label; setting UNSAFE_MODE to true removes that restriction. The repository includes a Makefile with npm-style targets, a unit test suite using mocked Keep clients, a manual smoke test against a real account, and GitHub Actions for linting, coverage and automatic semantic-version publishing to PyPI.

https://github.com/feuerdev/keep-mcp

mcpgoogle-keepnoteschecklistsgkeepapipython

Also in Knowledge & Memory

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 ...

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...