Software engineer in Yokohama, Japan — building local-first AI tooling
for Obsidian, the terminal, and the desktop.
- 🧠 AI that stays on your machine — LLM chat, RAG, and workflow automation that run against your own vault, your own files, your own keys.
- 🔌 Obsidian plugins — a family of "Hub" plugins bringing chat, MCP servers, semantic search, dashboards, and WYSIWYG editing into the vault.
- 🛠️ Small, dependency-free Go tools — MCP servers, log monitors, file watchers. Single binary, no runtime.
- ⌨️ Neovim & editor tooling — because the editor is where the work happens.
|
A local-first desktop workspace that turns your notes, documents, and workflows into context for AI. Everything I've learned from the Obsidian plugins, rebuilt as a standalone app — your files stay yours, the AI comes to them. This is where most of my energy goes from here on. → Extended by gemihub-gdrive, hub-ronginus, hub-accounting, hub-audio-score |
One responsive workspace for everything in your vault: Obsidian Bases, Kanban boards, calendars, timelines, web pages, and password-protected secrets. Linked memos work across notes, PDFs and EPUBs — so you can plan projects, annotate documents and track events without ever leaving Obsidian. |
The other half of my time goes here. One idea, three engines — pick the one that matches how you want your AI to run, then plug the companion plugins into it.
|
Google Gemini, desktop and mobile. AI chat, workflow automation, RAG, and an LLM Wiki (OKF). |
🔀 LLM HubBring your own backend: Gemini, OpenAI, OpenRouter, Grok, Ollama, or a CLI — all behind one UI. |
Fully private, no cloud required. Vault tools, MCP servers, RAG, encryption, and edit history. |
Companion plugins connect to whichever engine you installed — they supply no models of their own, they borrow yours:
- 🗣️ Discussion Hub — AI plugins register their models at runtime, so models from different providers can argue in the same structured discussion. Assign roles, run turns, let them conclude, then have a separate set of voters pick a winner.
- 📊 Dashboard Hub — AI is optional, but connect an engine and it can answer questions about selected text or reading memos, generate and edit a Base, rewrite Timeline posts, and build and run Workflows. It shares its Base directory and Timeline name with the connected plugin, so date-based questions read one day's file instead of scanning everything.
🧩 Beyond the pinned repos
Obsidian / knowledge tools — obsidian-wysimark (WYSIWYG Markdown editing that keeps files pure Markdown), obsidian-work-log, obsidian-gitlog-summary, obsidian-gdrive-vault, obsidian-gemihub
GemiHub ecosystem — gemihub-gdrive (Drive sync), hub-ronginus (AI debate arena), hub-accounting (Beancount-compatible bookkeeping), hub-audio-score (audio → sheet music), llm-hub-skills
Go & infra — mcp-gatekeeper (sandboxed MCP server with policy control), ragujuary (RAG on Gemini File Search), logmon-go, minipdfsplit, mcp-gcal, go-touch, touch_and_go
Editor & web — nvim-gemini-helper (Gemini + RAG in Neovim), http-file.nvim, wysimark-lite, mdwys, chrome-skk-lite, socket.io-reqev, svg_canvas_chart
✍️ I write about AI tooling and development on Zenn — issues and PRs are always welcome on any of my repos.