Tasks are scoped to the current project directory and stored in .claude-tasks/tasks.db (gitignored). Claude Code connects to the server via stdio and can create, update, and query tasks as you work.
Your Hugo blog is ground truth. hugo-memex indexes it into a SQLite cache with full-text search, taxonomy queries, and JSON front matter extraction : then exposes it via MCP so AI assistants can query ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results