Discover products

SpeakType — Privacy-first, offline voice dictation for macOS. Powered by WhisperKit AI, everything runs 100% locally on your Mac.

A native macOS command center with on-device AI, window management, clipboard intelligence, and dictation. Free forever. Pro is $29.99 once, for two Macs.

A tiny macOS menu bar app that tracks AI coding-provider usage windows, credits, costs, and resets across 56.

A macOS app that reads along with you and explains the allusions, references, and lost vocabulary you'd otherwise.

A native macOS Markdown editor with live PDF preview, AI workspace, vault support, LaTeX, Mermaid diagrams, and.

MacVisor runs macOS and Linux VMs on Apple Silicon, and Windows 11 and AI sandboxes as Tech Previews, with snapshots, templates, flexible storage, advanced networking, guest tools, and CLI automation.

Camera gear inventory, now with a native macOS app

Make retro-style 2D games fast with LunarBasic, a simple BASIC language that compiles straight to native, dependency-free executables for Windows and macOS.

TypeSeer is a system-wide AI autocomplete for macOS. It finishes your sentences as grey text in any app, learns how you write, and keeps up in 15 languages. The AI runs on your Mac, so nothing you type leaves your device.

Dodosend is a free, keyboard-first desktop email client for Gmail on macOS, Windows, and Linux, with a command palette that reads what you type. Now in private beta.

Tabbit is an AI-native browser that understands your context. Chat with webpages, automate tasks with Agent, create custom Skills, and organize tabs effortlessly. Supports GPT-5.4, Gemini-3.1-Pro, Claude-Sonnet-4.6, DeepSeek V4.0, Doubao-Seed-2.0, Kimi-K2.6, Qwen3.5-Plus, GLM-5.2, MiniMax-M2.7. Free download for macOS & Windows.

Plug in a MIDI keyboard and train sight-reading, chords, intervals and scales with live feedback, exam mode and games. Buy once. macOS, Windows, Linux.

smartly turns a plain English sentence into one executable shell command. macOS and Linux, directory and git aware, four model providers, a --learn mode that explains the command, and auto-run by default — with confirm and confirm-destructive modes when you want a gate.

A free, local macOS app that puts every Claude Code and Codex session in one window. See what each is doing, answer the ones waiting, start new ones, and keep hundreds organized. No account, nothing uploaded.

Speak naturally. Write instantly. Free, open source voice-to-text for macOS with on-device AI, adaptive tone, and.

Native to macOS, private by default, and built on plain Markdown files. No databases, no lock-in, just your files.

Free, open source macOS prompt launcher. One gesture to paste your saved prompts into ChatGPT, Claude, or any AI tool.

a free, open-source, fully native macOS app for Apple's container platform — containers, images, volumes and.

A native macOS client for App Store Connect. Track sales, revenue, subscriptions and manage reviews with on-device AI..

A WebKit browser for macOS, built for people who care about the details. Join the waitlist for early access.

Your goal. Delivered. RunAI Coder for Windows, macOS, Linux, Android, with iOS coming soon.

A native macOS terminal that speaks plain English. Approve AI-proposed commands, fix and explain errors, and use.

Orchestrate multiple AI agents, terminals, sketches and notes on one infinite canvas. Built for macOS.

The agent-native macOS IDE that drives your installed Claude Code — parallel agent lanes, team chat, multi-repo.

A local-first entertainment system: track a manga and book library on your own machine, then turn chapters into narrated recap videos. Desktop app for macOS.

Turn your voice into perfectly formatted text in any macOS app. EdgeWhisper is powered by Voxtral AI from Mistral —.

Create polished content quickly on your Mac.

A specialized Model Context Protocol server for MacOS. Give your agents direct access to the system voice engine.

crystl is a macOS terminal built for AI coding agents, including Claude Code, Codex, and Antigravity CLI. Organize.

A native macOS inference server built on MLX. Paged SSD KV caching drops agent TTFT from 30-90s to under 5s.