Caret vs Rowboat

Caret brings system-wide AI autocomplete to macOS with a single keystroke: Tab. Unlike tools that require you to open a specific app or switch contexts, Caret operates at the OS input layer — any text field, any application, anywhere on your Mac. It reads the surrounding text for context and offers completions inline, with zero UI chrome. The implementation uses macOS Accessibility APIs to hook into the text input stack across all applications. Context is gathered from the active window's text content, and completions are generated via a cloud LLM (with local model support on the roadmap). There's no menu bar app cluttering your workflow — just Tab when you want help, nothing when you don't. The simplicity is the product. While Raycast, Copilot, and similar tools add layers of UI, Caret bets that the right abstraction is "Tab, everywhere." For high-volume writers, support staff, and developers who live in diverse tools all day, this is the kind of ambient AI that actually reduces friction rather than adding it.

Rowboat is a local-first, open-source AI coworker that connects to your email and meeting notes, builds a persistent Obsidian-compatible knowledge graph from them, and uses that context to draft documents, meeting briefs, slide decks, and emails. It works with local models via Ollama or LM Studio, or with hosted APIs, and supports MCP for connecting external tools. The design philosophy is deliberately anti-cloud: all data stays in plain text Markdown files you can read, grep, and version-control. The knowledge graph is transparent — you can open it in Obsidian and see exactly what the AI knows about you. No black-box embeddings in a proprietary vector store, no "trust us with your emails" data agreements. Rowboat implements what Karpathy described as a "long-term memory coworker" — an AI that compounds value over time because it actually knows your history, your projects, and your terminology. TypeScript codebase, Apache 2.0 license, surging on GitHub trending this week.