MCP servers for persistent-memory

MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server;

Local-first MCP memory server — Memory + CodeGraph + Wiki in one SQLite file. Tree-sitter code indexing, markdown wiki, lifecycle hooks, auto-capture. No API key, no cloud.

Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it