mcp-memory-service and mcp-memory-keeper

These are competitors offering alternative approaches to persistent memory for AI agents—one targeting multi-framework pipelines with knowledge graphs and REST APIs, the other specialized for coding assistants with context management—where you would select based on your agent architecture and use case rather than use together.

mcp-memory-service
73
Verified
mcp-memory-keeper
61
Established
Maintenance 25/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 10/25
Adoption 9/25
Maturity 24/25
Community 18/25
Stars: 1,504
Forks: 215
Downloads:
Commits (30d): 153
Language: Python
License: Apache-2.0
Stars: 102
Forks: 19
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No Package No Dependents
No risk flags

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 mcp-memory-keeper

mkreyman/mcp-memory-keeper

MCP server for persistent context management in AI coding assistants

Provides a SQLite-backed persistent memory layer using the Model Context Protocol (MCP), enabling Claude to save and restore context across sessions through channels (auto-derived from git branches), checkpoints, and typed relationships between stored items. Integrates with Claude Code via stdio transport and includes batch operations, smart compaction, full-text search, and real-time change tracking to preserve architectural decisions and progress without manual intervention.

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