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
agentset-ai/mcp-server
Agentset MCP is a Node package that exposes Agentset, an open-source platform for Retrieval-Augmented Generation, to Model Context Protocol clients. Agentset stores documents in namespaces and answers queries against them, and this server makes that retrieval available as an MCP tool, so an assistant such as Claude Desktop can search a document collection while answering. The server runs without a separate installation step through npx, yarn dlx or pnpm dlx, and is published on npm as @agentset/mcp. It authenticates with an Agentset API key supplied in the AGENTSET_API_KEY environment variable and needs a namespace identifier, given either on the command line with the --ns flag or through the AGENTSET_NAMESPACE_ID environment variable. The README shows the matching mcpServers block for the Claude Desktop configuration file, where the command is npx and both values are passed through env. Two further options tune the behaviour. The -d flag replaces the description that the retrieval tool advertises to the model, which lets an integrator explain what the indexed corpus contains and when the assistant should reach for it. The -t flag passes a tenant identifier, so a single namespace shared by several customers can be queried on behalf of one of them, which suits multi-tenant products where each end user must only see their own documents. The repository is small and mostly wraps the hosted Agentset API rather than implementing retrieval itself; the full API reference lives in the Agentset documentation site. It targets developers already using Agentset who want their RAG corpus reachable from any MCP-compatible assistant instead of only through their own application code, and teams prototyping document-grounded assistants who prefer a hosted index over running a vector database themselves.
https://github.com/agentset-ai/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...