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
arabold/docs-mcp-server
The Grounded Docs MCP Server is an open-source project designed to enhance AI coding assistants by providing them with an always-current, personal knowledge base of third-party documentation. It addresses common issues faced by AI coding assistants such as outdated knowledge, hallucinations, version ambiguity, and the overhead of verifying AI-generated code. The server indexes documentation from multiple sources including websites, GitHub repositories, npm, PyPI, and local files, making it possible for AI agents to access the latest official documentation relevant to specific library versions. This version-aware search capability ensures that the AI's responses are accurate and aligned with the exact dependencies of a project, reducing bugs and improving code reliability. Key features include semantic chunking of documentation to preserve logical sections like headings, code blocks, and tables, which helps the AI understand context better. The server supports various embedding models from providers such as OpenAI, Google Gemini/Vertex AI, Azure OpenAI, and AWS Bedrock, with vector search as an optional feature. It also offers enterprise-grade authentication via OAuth2/OIDC and a user-friendly web interface for managing and searching documentation. The server runs locally, ensuring privacy and data security, and can be deployed easily using Docker or npx commands. The project supports integration with MCP-compatible clients like Claude, Cline, and Roo, allowing seamless incorporation into existing AI assistant workflows. Users can add new documentation through the web interface or via MCP tools, and the server provides CLI commands for listing, searching, and scraping documentation. Overall, the Grounded Docs MCP Server significantly boosts developer productivity by delivering trustworthy, version-specific documentation directly to AI coding assistants, minimizing errors and enhancing the quality of generated code.
https://github.com/arabold/docs-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...