mcp-memory-service and nocturne_memory
These are competitors—both provide persistent memory backends for AI agents with graph-based architectures, so you would select one based on preferences around consolidation strategies (A's autonomous consolidation vs. B's rollbackable versioning) rather than using them together.
About mcp-memory-service
doobidoo/mcp-memory-service
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
Consolidates multi-agent memory using a knowledge graph with typed edges (causes, fixes, contradicts) and autonomous compression, accessible via REST API with ONNX-based embeddings that run locally. Implements Remote MCP support for browser-based claude.ai integration via Server-Sent Events, alongside traditional desktop MCP, with OAuth 2.0 authentication and self-hosted infrastructure (no cloud lock-in). Agent identity is tracked via `X-Agent-ID` headers for scoped retrieval, and conversation threading is preserved through `conversation_id` fields, enabling both shared memory across agent fleets and inter-agent messaging through semantic tag-based filtering.
About nocturne_memory
Dataojitori/nocturne_memory
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
Implements a graph-based memory architecture with SQLite/PostgreSQL backends, where AI agents can create, update, and rollback their own structured memories through MCP—eliminating vector RAG's semantic lossy compression and enabling condition-triggered disclosure of hierarchical knowledge graphs with human-auditable versioning. Includes a visual dashboard for memory exploration, diff review, and governance; integrates natively with Claude Desktop, Cursor, and other MCP-compatible frameworks as a direct OpenClaw replacement.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work