Cavemem offers a local-first persistent memory layer for AI coding assistants, compressing session data with a deterministic grammar to reduce token count by 75%. It stores observations in SQLite with hybrid search and runs without a daemon.
Supermemory replaces traditional RAG stacks with a unified AI memory layer, offering fast, hybrid memory retrieval and automatic fact extraction in ~50ms. Here’s how it works and how to try it.
Claude OS cuts codebase indexing from hours to seconds using hybrid tree-sitter parsing, enabling fast persistent AI memory for Claude Code projects with local-first data storage.
Memcord is a self-hosted MCP server enabling local-first AI memory with slot-based context isolation and multiple summarization backends, designed for privacy and developer ergonomics.
MemPalace offers a local-first AI memory system with 96.6% recall on conversation history retrieval without any cloud or LLM calls, emphasizing privacy and efficient semantic search.
