memora and universal-memory-mcp
About memora
agentic-box/memora
Give your AI agents persistent memory — MCP server for semantic storage, knowledge graphs, and cross-session context
This project helps AI agents remember information across different tasks and conversations, acting like a persistent brain. It takes in structured notes, conversations, and observations, then organizes them into a searchable memory and a visual knowledge graph. AI developers or researchers building sophisticated agents that need long-term context and recall would use this.
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