LLM Knowledge Base / RAG
An offline-first, event-sourced knowledge system: it captures text (a global hotkey on Windows), organizes it with a local LLM (Ollama) into a semantically linked Obsidian Markdown vault, and auto-generates dependency-ordered plans via a Kahn topological sort. The platform-agnostic core runs fully offline.
An offline-first personal knowledge system. It captures text from any app, organizes it with a local LLM (Ollama) into a lossless, semantically linked Markdown vault, and auto-generates dependency-ordered plans via topological DAG sort.
Under the hood it’s an event-sourced graph — append-only events with deterministic projections to plans, calendars, and CSV — using a ports-and-adapters design for swappable backends. The vault is exposed to AI agents through a local Model Context Protocol (MCP) server.