mcp-memory-keeper and MegaMemory
MegaMemory is a more feature-rich implementation and extension of the core persistent context management server concept introduced by mcp-memory-keeper, offering semantic search, in-process embeddings, and a web explorer on top of the base MCP server functionality.
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.
About MegaMemory
0xK3vin/MegaMemory
Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.
Uses in-process ONNX embeddings (all-MiniLM-L6-v2) and SQLite with WAL for zero-dependency semantic search and persistence. Operates as an MCP stdio server integrated with Claude Code, OpenCode, Antigravity, and Codex, with built-in two-way merge conflict resolution for collaborative knowledge graph management across branches. The LLM itself acts as the indexer—concepts are stored in natural language rather than parsed code symbols—enabling agents to update the graph after each task and query semantic context before starting new ones.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work