MCP servers for long-term memory and vector search: store notes, embeddings and facts so an AI assistant remembers across sessions. 799 servers in this category.
Provides typed long-term memory for AI agents by extracting, ranking, and consolidating durable facts from conversations.
Provides AI agents with a private, local Markdown-based knowledge graph and searchable SQLite memory.
Provides a shared, governed memory layer for AI agents and teams using PostgreSQL and pgvector for persistent, multi-project context.
Provides tiered, local-first AI memory for storing and retrieving episodes, facts, preferences, and reflections across different AI clients.
Connects Joplin notes to AI clients via MCP to provide semantic search and a centralized memory engine for multi-agent workflows.
Provides shared long-term memory for AI coding agents using a local SQLite database with hybrid semantic and keyword search.
Provides a shared long-term memory vault and public knowledge archive for AI agents to access methods and application reports.
$claude mcp add --transport http openakashic https://knowledge.openakashic.com/mcp/
Provides a shared, persistent memory layer for LLMs to store and retrieve documents, knowledge, and notes across different MCP-compatible clients.
Provides a local-first persistent memory layer that allows AI coding agents to remember project context, technical decisions, and developer preferences.
Indexes a local codebase and lets an AI client run semantic code, docs, and Git history searches offline.
$claude mcp add code-memory -- uvx code-memory
Provides a fully local, zero-config long-term memory server for MCP clients on macOS using on-device embeddings and Chroma.
Provides AI assistants with persistent, local-first long-term memory using hybrid vector and keyword search across codebases.
Provides a shared local SQLite database for AI agents to store and recall long-term memories across different sessions and clients.
Provides AI agents with persistent semantic memory and a hierarchical knowledge base through a unified MCP gateway.
Provides a unified memory surface combining semantic facts and a code knowledge graph to enable cross-linked recall between facts and code symbols.
Provides local web search via SearXNG and persistent memory management for coding agents using disk-based storage and hybrid semantic search.
Provides semantic search over a local ChromaDB knowledge base with citations for any MCP-compatible AI client.
Provides memory tools for AI agent frameworks including remember, document, recall, and relate via MCP or HTTP.
Provides a local-first memory runtime for AI agents that stores revisioned claims linked to evidence with strict authorization scopes.
Provides a temporal memory core that allows AI clients to read and write structured, time-decayed personal and operational memories.