nocturne_memory and mind-mem

These are **competitors** offering different architectural approaches to agent memory—one emphasizing visual graph-structured persistence with rollback capabilities, the other prioritizing hybrid retrieval (BM25 + vector) with contradiction detection and auditing—where you'd select based on whether you need deterministic replay or contradiction-safe reasoning.

nocturne_memory
63
Established
mind-mem
54
Established
Maintenance 25/25
Adoption 10/25
Maturity 9/25
Community 19/25
Maintenance 13/25
Adoption 10/25
Maturity 18/25
Community 13/25
Stars: 615
Forks: 79
Downloads:
Commits (30d): 101
Language: Python
License: MIT
Stars: 5
Forks: 2
Downloads: 385
Commits (30d): 0
Language: Python
License: Apache-2.0
No Package No Dependents
No Dependents

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 mind-mem

star-ga/mind-mem

Persistent, auditable, contradiction-safe memory for coding agents. Hybrid BM25 + vector retrieval, 19 MCP tools, co-retrieval graph, MIND-accelerated scoring. Zero external dependencies.

Implements shared memory across all MCP-compatible AI agents (Claude Code, Cursor, Windsurf, etc.) via a single SQLite workspace with concurrent-safe WAL mode. Core architecture combines BM25F full-text + vector retrieval with RRF fusion and intent-aware routing, plus a co-retrieval graph using PageRank-style propagation to surface structurally-related blocks. Includes active contradiction detection, drift analysis, and deterministic governance—all Markdown-backed with full audit trails and zero external dependencies.

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