Show HN: SQLite Memory – Markdown based AI agent memory with offline-first sync
Category: database
Tags: sqlite, ai-agents, vector-search, offline-first, embeddings
Score: 7.5/10 (Innovation: 7, Technical: 8, Documentation: 8, Utility: 7)
SQLite Memory is a C-language SQLite extension that provides AI agents with persistent, searchable memory using markdown files as a source of truth. It's interesting because it combines local-first vector embeddings (via llama.cpp), hybrid semantic/full-text search, and offline-first sync to create a portable, zero-infrastructure memory system for distributed AI agents.
Target audience: AI/ML engineers, backend devs, application developers building agent systems
Repository: https://github.com/sqliteai/sqlite-memory · C · NOASSERTION · 17 stars
View on Hacker News