nocturne_memory and MegaMemory

These are competitors—both provide persistent memory systems for MCP agents with semantic/structured retrieval capabilities, but nocturne_memory emphasizes graph-like rollbackable storage while MegaMemory focuses on project-specific knowledge graphs with embedded semantic search.

nocturne_memory
67
Established
MegaMemory
50
Established
Maintenance 25/25
Adoption 10/25
Maturity 13/25
Community 19/25
Maintenance 10/25
Adoption 8/25
Maturity 20/25
Community 12/25
Stars: 615
Forks: 79
Downloads:
Commits (30d): 101
Language: Python
License: MIT
Stars: 59
Forks: 7
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No Package No Dependents
No risk flags

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.

About MegaMemory

0xK3vin/MegaMemory

Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.

Uses in-process ONNX embeddings (all-MiniLM-L6-v2) and SQLite with WAL for zero-dependency semantic search and persistence. Operates as an MCP stdio server integrated with Claude Code, OpenCode, Antigravity, and Codex, with built-in two-way merge conflict resolution for collaborative knowledge graph management across branches. The LLM itself acts as the indexer—concepts are stored in natural language rather than parsed code symbols—enabling agents to update the graph after each task and query semantic context before starting new ones.

Scores updated daily from GitHub, PyPI, and npm data. How scores work