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
madarco/ragrabbit
RagRabbit is a self-hosted AI site search that indexes your own content and then makes it available to both site visitors and AI clients. It is a Next.js application organised as a Turborepo, built on LlamaIndex TypeScript with pgvector inside PostgreSQL, and it can be deployed to Vercel in one click or run anywhere with Node.js 20, a pgvector-enabled PostgreSQL and an OpenAI API key, with Trigger.dev optional. Content enters through the indexing section, where a single URL or a whole website can be crawled recursively; a job runner tab processes the queue and must stay open until it finishes. From the resulting index the app generates an llms.txt file that is fully customisable, including reordering its table of contents, and previewable in the UI. Two embeddable front ends are provided: a chat button added with a single widget.js script tag, and an inline search input placed anywhere on a page with the ragrabbit-search custom element, which can also be mounted in React through next/script. The part that concerns MCP is the packages/mcp-server workspace, published as @ragrabbit/mcp and run with npx, which exposes the crawled and indexed documentation as an MCP server so Claude Desktop and Cursor IDE can query the same corpus that powers the on-site widget. Access control covers username and password login, email login through Resend with an optional allowlist of addresses and a mode that logs the sign-in link instead of sending mail, plus API key access; environment variables for all of this are listed in the example env file. A Fumadocs integration is documented. The project fits teams who want documentation search, an llms.txt endpoint and an MCP endpoint over their own site without handing the content to a hosted service.
https://github.com/madarco/ragrabbit
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...