Leo Health Core is a zero-dependency Python CLI for parsing large Apple Health XML and Whoop CSV exports into a unified SQLite DB, using SAX streaming parsing and local file watching for seamless ingestion.
Mind offers a SQLite-backed persistent memory layer with a 3-tier model for AI agents, solving context decay via checkpoint recovery and semantic search integration.
Reconya is a native Go network reconnaissance tool combining ICMP, TCP, and ARP scanning with a vanilla JS web dashboard. Docker support is experimental due to Layer 2 limits.
Scarf is a Swift native macOS and iOS app that provides a GUI for the Hermes AI agent, featuring SSH connectivity, efficient image encoding, SQLite state sync, and real-time dashboards.
Windrecorder captures screen activity on Windows, indexes it with multiple OCR engines locally, and offers a searchable rewind UI—all without cloud dependencies.
TokenTracker is a local-first CLI tool that aggregates token usage and costs from 13 AI coding agents using a hook-based architecture and serves a local dashboard with detailed analytics.
Mercury Agent is a TypeScript AI assistant with a persistent SQLite-based memory system, permission-hardened tools, and extensible skills, designed for safe, adaptive 24/7 operation via CLI or Telegram.
