memory-journal-mcp and universal-memory-mcp
About memory-journal-mcp
neverinfamous/memory-journal-mcp
MCP Server for AI Context + Project Intelligence. Overcome Disconnected AI Sessions with Persistent Project Memory, Automatic Session Briefing & Summation, Triple Search, Knowledge Graphs, GitHub Integration (Actions, Insights, Issues, Kanban, Milestones, and PRs), Automated Scheduling, 42 Tools, Tool Filtering, and HTTP/SSE & stdio Transport.
Persists project context across AI sessions using SQLite with full-text and semantic vector search (HuggingFace transformers + sqlite-vec), enabling agents to auto-brief from history and hand off context via structured session summaries. Provides 61 MCP tools organized in 10 groups including GitHub Commander for automated issue triage, PR review, and audit workflows, plus dynamic multi-repo routing via PROJECT_REGISTRY for managing multiple projects with a single server instance. Architecture emphasizes structured error handling with classification codes and recovery hints for agent reliability, backed by 96.7% test coverage and Alpine Docker deployment.
About universal-memory-mcp
slicenferqin/universal-memory-mcp
超级个人助理 - 通用、跨项目、100%本地私有的AI记忆系统（基于MCP协议）- Super personal assistant for any AI CLI - Universal, cross-project, 100% local & private via MCP
Implements a three-tier memory architecture (sensory → short-term → long-term) with automated daily extraction and weekly consolidation, using SQLite vector indexing for semantic + keyword hybrid search with sub-5ms latency. Operates as an MCP server compatible with Claude Code, OpenCode, Copilot, and other AI CLIs, storing all data locally with automatic lifecycle management (archival after 30+ days) and optional project-specific relevance weighting.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work