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
vectorize-io/vectorize-mcp-server
Vectorize MCP Server is a JavaScript implementation of the Model Context Protocol that connects an MCP client to the Vectorize retrieval platform. It is distributed on npm as @vectorize-io/vectorize-mcp-server and is normally launched with npx, so no local build is required. Three environment variables configure it: VECTORIZE_ORG_ID identifies the organization, VECTORIZE_TOKEN carries the API credential, and VECTORIZE_PIPELINE_ID selects the retrieval pipeline the tools operate against. The server publishes three tools that map onto the Vectorize HTTP API. The retrieve tool performs a vector search and returns matching documents for a natural language question, with a k parameter controlling how many results come back, which is the usual building block for retrieval augmented generation inside a chat client. The extract tool accepts a base64 encoded document together with its content type, for example application/pdf, and returns the extracted text already chunked into Markdown, letting an agent ingest file formats it could not otherwise read. The deep-research tool generates a research report from the pipeline for a given query and can optionally combine the private pipeline content with web search. The README documents installation across several hosts: one-click install links and a User Settings JSON block for Visual Studio Code and VS Code Insiders, a workspace level .vscode/mcp.json file for sharing the configuration with a team, and the equivalent mcpServers entry for Claude Desktop, Windsurf, Cursor and Cline, all with prompted inputs so the token is not stored in plain text. Development uses npm install and npm run dev, and releases are cut by bumping the package version and pushing a matching tag. The audience is teams already running Vectorize pipelines who want an assistant to search their indexed content, turn uploaded files into Markdown chunks and produce reports grounded in their own corpus.
https://github.com/vectorize-io/vectorize-mcp-server
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...