MegaMemory and simple-memory-mcp
About MegaMemory
0xK3vin/MegaMemory
Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.
MegaMemory helps AI coding agents remember project details across different work sessions. It takes natural language descriptions of code concepts, architecture, and decisions, then allows the agent to semantically search and recall these details for future tasks. This tool is for developers who use AI coding assistants like OpenAI Codex, Claude Code, or Antigravity and want them to maintain a consistent understanding of a project over time.
About simple-memory-mcp
chrisribe/simple-memory-mcp
🧠 Blazingly fast persistent memory for AI assistants. Sub-millisecond SQLite storage with smart tagging, full-text search, and automatic relationships. MCP server + CLI.
Implements an MCP server with a GraphQL interface for memory operations, storing data in local SQLite with BM25 full-text search scoring rather than embeddings. Integrates directly with Claude Desktop and VS Code via MCP protocol, plus includes a CLI for manual queries and a web interface for browsing stored memories. Designed as a lightweight alternative to RAG systems for single-user local knowledge management without vector databases or cloud dependencies.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work