I built a memory system for Claude that solves the context loss problem many of you face with Claude Code. The problem: Every Claude Code session starts from scratch. You explain your architecture, past decisions, coding standards - then hit context limits and lose everything. The solution: BuildAutomata Memory is an MCP server that gives Claude persistent, versioned memory across sessions. What makes it different:

Dual-layer architecture: SQLite + Qdrant vector search Git-style versioning: Full history with diff tracking Memory access patterns: Importance decay + usage tracking Timeline visualization: See how knowledge evolved CLI + MCP: Works with Claude Desktop AND Claude Code

Already validated: 100+ memories, 0.9MB database, working in production across three Claude interfaces (Desktop, Code, Cursor). GitHub: [https://github.com/brucepro/buildautomata_memory_mcp] Gumroad: [https://brucepro1.gumroad.com/l/zizjl] Happy to answer questions about the architecture or the Ego persona system it evolved from (Memoir v1 → BuildAutomata v2).