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
run-llama/mcp-server-llamacloud
LlamaCloud MCP Server is a TypeScript MCP server that puts managed indexes hosted on LlamaCloud behind MCP tools. Its distinguishing feature is that one process can serve several indexes at once: each index named on the command line becomes its own tool, so a client sees separate, individually described retrieval tools rather than a single generic search endpoint. Indexes are declared as pairs of --index and --description arguments, with an optional --topK to cap how many results that index returns, and the server derives a tool name from the index name in the form get_information_index_name. Every generated tool takes a single query parameter and runs it against its own index, which lets a model choose the right corpus from the descriptions alone. Configuration goes into the MCP client config file, where the server is launched with npx and the package @llamaindex/mcp-server-llamacloud; a LLAMA_CLOUD_API_KEY environment variable is required, and LLAMA_CLOUD_PROJECT_NAME is optional and defaults to Default. The README lists the config file locations for Claude Desktop on macOS and Windows and notes that Windsurf and Cursor are configured the same way. For development the project is built with npm run build, has a watch mode for automatic rebuilds, and can be pointed at the local build by replacing the npx invocation with node ./build/index.js; the MCP Inspector is wired up as an npm script for debugging the stdio transport. The repository carries a caution notice stating that the project is archived and no longer supported, with a pointer to the LlamaIndex documentation for current ways of connecting an agent to LlamaParse platform APIs. It remains a compact example of exposing per-corpus retrieval tools over MCP.
https://github.com/run-llama/mcp-server-llamacloud
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...