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
nkapila6/mcp-local-rag
mcp-local-rag is a Python Model Context Protocol server that gives a language model a retrieval-augmented web search tool while running entirely on the local machine. When the model calls a search tool, the server queries a search backend, fetches the returned results, computes embeddings with Google's MediaPipe text embedder, ranks the entries by semantic similarity to the query, selects the top k, extracts the content of those pages and returns it to the model as Markdown. Because both the search and the embedding step run locally, no API key or hosted service is involved. The server supports more than nine search backends, including DuckDuckGo, Google, Bing, Brave, Wikipedia, Yahoo, Yandex, Mojeek and Grokipedia, so a caller can pick privacy-focused engines or broader ones depending on the task. Beyond single queries it offers deep research tools that issue several related queries across multiple engines at once: deep_research for a general multi-engine sweep, deep_research_google for technical and scientific questions that benefit from Google's index, and deep_research_ddgs for private research through DuckDuckGo. Two lighter tools, rag_search_ddgs and rag_search_google, handle quick single searches. Backends and result limits are configurable per call. The server runs directly through uvx from the git repository, or from a published Docker image, and is registered in the usual MCP client configuration file; the README documents Claude Desktop, LM Studio and Raycast setups. The repository also ships an agent skill called local-rag-search that instructs a model on when to pick a quick search over deep research, how to phrase queries, and how to tune the num_results, top_k and backend parameters. It suits users who want web grounding for a local assistant without sending queries through a commercial search API.
https://github.com/nkapila6/mcp-local-rag
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...