"Using ChromaDB and Neo4j for persistent memory storage" matching MCP servers:

Gives Claude Code long-term memory that persists across sessions via hybrid BM25 and vector semantic search, with multi-project isolation.

Provides persistent, inspectable memory storage for AI agents using SQLite. Agents can store, recall, and search memories across sessions via three MCP tools.

Turns a codebase into a persistent knowledge graph so AI coding agents can answer structural questions about functions, call chains, routes, and cross-service links through graph queries instead of reading files one by one.

Enables Codex to manage macOS local and cloud storage by indexing files, planning moves or copies, executing them with SHA-256 verification, and requiring explicit confirmation before deleting local originals.

A single local MCP gateway for Neo4j that exposes both proxied generic Neo4j tools (schema, Cypher, GDS) and custom YAML-defined use-case tools behind one stdio endpoint.

Enables AI assistants to execute shell commands and manage long-running processes within persistent tmux sessions across isolated workspaces. It features a dual-window architecture to separate raw command execution from interactive terminal output.

A lightweight memory layer for MCP servers that persists user context across LLM sessions with minimal token cost, supporting key-value dedup, multi-tenant namespaces, and optional TTL.

Enables querying a Neo4j knowledge graph built from Git repositories and relational database schemas via MCP, with tools for schema inspection, Cypher queries, and searching code and database entities.

A local-first MCP server providing persistent, searchable knowledge base via SQLite, enabling AI agents to save and recall facts across sessions without cloud dependencies.

Enables fetching weather forecasts for the USA via NWS API and for Israel via browser automation using Playwright.

Enables querying and modifying a local MySQL database and a Neo4j knowledge graph through separate read-only and read-write tools, with permissions scoped by database user and Neo4j transaction mode. Lets clients run SELECT statements against MySQL, execute inserts/updates/deletes, and run read or write Cypher queries.

Enables interaction with Neo4j databases from the Cursor IDE by executing Cypher queries, managing connections, and retrieving database information.

Slipstream - Built by Vektor Memory - a persistent multi-layered memory architecture. 4-layer associative graph memory (MAGMA) with autonomous REM cycle, CLI, DXT-MCP Cloak Tools.

Provides a local SQLite-backed code context knowledge base with MCP tools for storing and querying code facts, call graphs, semantic info, evidence, and business mappings, plus versioned snapshot publishing and incremental sync.

MCP server providing durable Substrate organizational memory tools, including search, read, query, ingest, remember, and sync. It integrates with Codex to automatically capture completed turns and session boundaries for persistent memory.

This read-only MCP Server allows you to connect to Neo4J data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for Neo4J (https://www.cdata.com/drivers/neo4j/download/mcp).

MCP server providing persistent memory management for AI agents using SQLite and FTS5, enabling storage, full-text search, and recall of memories with namespace isolation.

Enables LLM clients to access crop yield predictions from RGB imagery, topic-based PDF literature, and soil lab/moisture CSV data.

Persistent semantic memory for AI agents, enabling storage, semantic search, knowledge graph connections, and inter-instance messaging across conversations using local models via Ollama.

Auto-captured, auto-recalled, path-scoped memory for AI coding agents and teams.