Show HN: ThreadShelf – Obsidian and AI chats: vector search, MCP, llama.cpp

ThreadShelf is a local-first archive that parses exports from ChatGPT, Claude, Google AI Studio, OpenRouter, LM Studio and Grok into a common format, embeds them locally and stores them in LanceDB for semantic and exact search. The same index is reachable through a React UI, CLI, HTTP API and an MCP stdio server, and archived threads can optionally be continued with a loopback-only llama.cpp GGUF model or the explicitly external OpenRouter provider. It also connects Markdown/Obsidian vaults for local note search and bounded tool-calling workflows, with vault writes off by default.