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.
Indexes a code repository so an AI client can retrieve task-relevant code context to improve prompts and reduce hallucination.
Provides persistent multimodal context storage for LLM agents with support for semantic, full-text, and hybrid search.
Provides AI agents with a shared local memory using a hierarchical book structure to store, recall, and cite conversation evidence.
Provides long-term memory for coding agents by maintaining a local archive, a Git-based wiki, and hot context for sessions.
Provides AI agents with a source-backed memory layer using Git citations, local retrieval, and conversation memory for verifiable project knowledge.
An MCP server and agent that let AI clients search and understand video, images, audio, and text.
Provides a shared memory layer for AI agents on Omarchy, allowing different harnesses to save and recall information across sessions.
Provides AI agents with long-term memory by recording chat histories, managing person rosters, and searching through markdown vaults.
Provides AI agents with persistent graph memory, token-saving data pointers, and a suite of cloud backend tools.
$claude mcp add --transport http cloud-backend https://mcp.neonia.io/mcp
Provides task-scoped memory retrieval, claim evaluation, and local audit records for MCP clients.
Transforms documents into a structured, searchable knowledge system using local vector search and multi-collection isolation.
Indexes conversation transcripts and artifacts using SQLite to enable cross-session search and subagent lineage tracking.
Provides a shared local memory palace for multiple AI agents using a SQLite database and standard MCP to maintain context across different models and platforms.
Provides a self-hosted memory for chat archives and activity streams by indexing conversations as segments for AI assistants via MCP.
Provides a self-hosted, auditable personal memory engine that uses an append-only log and verifiable excerpts to prevent AI hallucinations.
Enables local semantic and keyword search across Obsidian vaults and source repositories using LanceDB and Ollama.
Provides persistent project and user memory with semantic search for AI coding agents like Claude Code, Cursor, and Codex.
Provides a self-hosted shared memory for AI coding assistants to store and retrieve project context and decisions via MCP.
Provides a local, shared memory server for AI coding agents to automatically remember project decisions and context across sessions.
Enables AI agents to perform local-first knowledge retrieval using hybrid SQLite FTS5 and LanceDB vector search with reranking.