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
pinkpixel-dev/mem0-mcp
mem0-mcp is a Model Context Protocol server that gives language model agents memory that survives across sessions by wrapping the Mem0 platform through the mem0ai Node.js SDK. It is published on npm as @pinkpixel/mem0-mcp and can be installed into Claude Desktop through Smithery. The server exposes a set of memory tools over MCP. add_memory stores plain text or structured role and content message arrays. search_memories runs semantic and BM25 hybrid search with filters, a similarity threshold, top-k and optional reranking, and search_memory remains as a backward-compatible alias. list_memories pages through stored records, while get_memory, update_memory and delete_memory operate on a single record by id and get_memory_history returns the audit trail of revisions. Every write and query can be scoped by userId, runId or sessionId, agentId and appId, and the server nests those identifiers inside the Mem0 V3 filters block automatically so the API does not reject them. Because cloud additions are processed asynchronously, add_memory polls the background queue until the job finishes by default with a configurable timeout, or returns an event id immediately when waitForCompletion is false; get_memory_event and list_memory_events inspect those background jobs. Bulk helpers cover batch_update_memories and batch_delete_memories, the latter requiring an explicit confirm flag, while rate_memory submits quality feedback and create_memory_export with get_memory_export drive asynchronous export jobs. get_memory_capabilities reports which features the active backend supports, because the server runs in three storage modes: Mem0 cloud with an API key, self-hosted Supabase with an OpenAI key for embeddings and SQL migrations supplied in the repository, or a non-persistent in-memory vector store for development and testing. It suits agent authors who want recall across sessions without building their own vector storage layer.
https://github.com/pinkpixel-dev/mem0-mcp
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...