Show HN: Vim-like, hyper-efficient, LLM power tool – 20-80k tokens not 350k+

I built a focused TUI tool for efficient parallelized tasks, early independent testers expressed 90%+ API savings and more direct results. This is accomplished by user smaller context windows, hybrid client-side compaction, tool compaction, and system nudges (to avoid polluting the base prompts).<p>My Shell features:<p>- Vim-inspired keybindings, your keys never have to leave the keyboard (some mouse control supported as well)<p>- Custom Markdown, LaTeX, and Mermaid rendering support<p>- On-demand subagents with LLM-directed context handoff<p>- Thread pooling, client-side compaction, tool compaction<p>- Supports Powershell without a degraded experience; also support VGA/VESA mode, run even when GPU drivers break!<p>- Single bundle, no external packages required<p>It’s opinionated, terminal-first, Vim-inspired; if that’s not for you, I have a web chat and a desktop app <i>coming soon</i>