MCP servers for long-term memory and vector search: store notes, embeddings and facts so an AI assistant remembers across sessions. 799 серверов в этой категории.
Вставьте ссылку на его GitHub repo, и мы добавим его после быстрой проверки.
Добавить сервер
Allows AI agents to store and retrieve verbatim Markdown and text notes locally to preserve original context across sessions.
$claude mcp add fidelis -- uvx fidelis-memory
Provides long-term memory and context selection for AI agents by storing messages and recalling them within specific token budgets without LLM calls.
$claude mcp add llmslim -- uvx llmslim
Provides a shared, local-first memory for AI coding agents to persist project decisions and lessons across different sessions and tools.
$claude mcp add yggdrasil -- uvx yggdrasil-memory
Provides AI agents with persistent memory using Markdown files, hybrid search, and a typed knowledge graph.
$claude mcp add inkwell-memory -- docker run -i --rm docker.io/foreigndmitryi/inkwell-memory:0.14.0
Provides AI assistants with local-first graph memory using SQLite and semantic search to recall, connect, and learn from long-term context.
$claude mcp add memory-engine-mcp -- docker run -i --rm ghcr.io/simoneb79/memory-engine-mcp:1.5.3
Provides local hybrid-search memory for AI agents using plain Markdown files and a SQLite index.
$claude mcp add cogvault -- uvx cogvault
Provides an agent memory database with MindQL queries, hybrid search, and a thought graph for AI clients.
$claude mcp add engrava-mcp -- uvx engrava-mcp
Provides a verifiable memory layer for coding agents that validates stored facts against the local filesystem and git history.
$claude mcp add bettermemory -- uvx bettermemory
Provides AI agents with long-term memory by capturing conversations verbatim and serving relevant context through a local hyperdimensional storage engine.
Lets an AI client build a governed knowledge graph from its own documents and answer questions with cited sources or abstain when evidence is missing.
$claude mcp add veritasgraph -- uvx veritasgraph-mcp
Provides AI agents with persistent, biological-inspired memory that uses Ebbinghaus decay, fact consolidation, and entity graphs for improved recall.
$claude mcp add cognitive-ai-memory -- docker run -i --rm ghcr.io/your-memory/cognitive-ai-memory:1.0.2
Gives AI clients one shared long-term memory to search, read the user profile, and add facts and documents.
$claude mcp add --transport http membase-3f9d69 https://api.app.membase.com/mcp-httpGives AI clients one shared long-term memory to add facts and documents, search past context, read the user profile, and ask questions.
$claude mcp add --transport http membase https://api.app.membase.com/mcp-http
Gives AI clients a local Markdown memory that recalls settled notes with citations and says when it does not know.
$https://github.com/398894496-arch/KRouter/releases/download/v2.1.2/KRouter.mcpb
Provides a self-hosted persistent cognitive memory layer for AI coding agents to store architecture decisions, schemas, and constraints.
Provides AI assistants with a two-tier memory system featuring a zero-latency hot cache and semantic search for persistent project knowledge.
$claude mcp add memory-mcp -- uvx hot-memory-mcp
Provides persistent memory and behavioral drift detection to help AI agents maintain identity and context across sessions.
$claude mcp add cathedral-mcp -- uvx cathedral-mcp
Enables AI applications to share a single unified memory for recalling, remembering, and forgetting information across different clients.
$claude mcp add dawnmere-connector -- npx -y dawnmere-connectorEnables multiple AI applications to share a single local memory for recalling, remembering, and forgetting information on macOS.
$claude mcp add dawnmere-connector -- npx -y dawnmere-connector
Lets an AI client semantically search local files and code, returning matching source text, and warm up search indexes.
$claude mcp add vexor -- uvx vexor