"memory" matching MCP servers:

Gives every AI agent on a machine a shared, local-first long-term memory: 16 tools to save, search, edit and organize structured notes in one SQLite file, with attribution per client. Runs over stdio or localhost HTTP, so Claude Code, omp and any other MCP client recall the same facts, decisions and entities.

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

Enables AI assistants to maintain a persistent, local memory using SQLite with ranked full-text search, German morphological matching, and two-axis filing, all without external services.

Embedded, local-first agent memory: facts extracted into a per-namespace SQLite file (vec0 + FTS5) with hybrid retrieval and point-in-time (time-travel) queries. ADD-only history over stdio — no server process, no cloud dependency.

A notes app that becomes your second brain. Open source, private, encrypted when you want it, and every file stays yours. Mac, Windows, Linux and self host!

MCP server providing persistent memory for AI applications, enabling Claude to store and recall memories with hybrid search and knowledge graph.

Hosted memory for AI agents that learns from outcomes, with shared rooms. One key across Claude, Cursor & ChatGPT.

A local-first MCP server that exposes personal notes and files as unified semantic context for AI agents via vector search and file monitoring.

Provides persistent memory for AI agents using hybrid search (vector embeddings + BM25) with neural reranking, enabling storage and retrieval of insights, debugging solutions, and patterns across coding sessions.

Enables multiple AI agents on one machine to write, search, fetch, link, and give feedback on a shared local store of Markdown-backed facts, preferences, and conventions that persists across sessions. Memories gain confidence as different hosts confirm their use and can be distilled into denser ones, so agents stop re-discovering the same context.

Long-term memory for AI coding agents, stored as a tree of plain local files. Agents search it before answering and save what lasts; changed facts are kept as history and flagged as outdated.

Provides brain-inspired long-term memory for MCP clients, enabling persistent user understanding across sessions with Chinese-optimized hybrid retrieval and evolving user profiles.

Gives AI coding agents persistent, evolving knowledge about a codebase, enabling them to store and retrieve observations about architecture, conventions, gotchas, and recent work context.

A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_rep

Persistent knowledge graph MCP server with SQLite backend, offering graph traversal, fuzzy search, and temporal queries for entities and relations. It serves as a drop-in replacement for the npm mcp-server-memory with enhanced capabilities.

An MCP server that implements memory with decay mechanics, allowing AI agents to store and retrieve memories that fade over time unless accessed, with a permanent journal for verification.

Automatically records AI conversation turns and code changes to local Markdown files to provide persistent context across chat sessions. It enables AI agents to search history through MCP tools and provides a web viewer for browsing past discussions.

Enables coding agents to query and modify a SQLite database through twelve SQL-based tools, with safety enforced server-side via statement policies, protected tables, result caps, and snapshots. It also provides an append-only, hash-chained memory log with checkpoints so agents can record events and resume context across sessions.

Enables agents to manage persistent long-term memory through MCP tools for searching, adding, updating, giving feedback, and forgetting memories, with automated pipelines for redaction, distillation, and reconciliation.

Cross-project memory sharing for Claude Code and Cowork. Stop teaching Claude the same thing twice.