qqqa for Mac

Fast, stateless LLM-powered assistant for your shell: qq answers; qa runs commands

Status: feature-complete, and thank you

qqqa started as a small itch: I was tired of switching to a browser for shell commands I always forget. Then it launched on Hacker News, drew 165 points and 86 comments, and went well past anything I expected. Today it has more than 600 stars on GitHub, it ships in Homebrew core, and it runs on macOS, Linux and Windows.

Much of qqqa came straight from that thread and the issues that followed: piped input, OpenRouter, local models through Ollama, Homebrew, privacy-first history, a tighter sandbox for qa, and support for Codex and Claude Code subscriptions. Thank you to everyone who starred it, filed an issue, sent a PR or argued about it on HN. You made it a much better tool.

With 1.1.0, qqqa does what it set out to do: quick answers and one-step tasks in your shell, fast, stateless, and out of your way. So it's done, on purpose. It stays on Homebrew and GitHub Releases, keeps building, and gets bug and security fixes; no new features are planned. Small PRs that fit its scope are still welcome. More in #61.

What is qqqa

qqqa is a two-in-one, stateless CLI tool that brings LLM assistance to the command line without ceremony.

The two binaries are: qq - ask a single question, e.g. "qq how can I recursively list all files in this directory" (qq stands for "quick question") qa - a single step agent that can optionally use tools to finish a task: read a file, write a file, or execute a command with confirmation (qa stands for "quick agent")

qqqa runs on macOS, Linux, and Windows.

By default the repo includes profiles for OpenRouter (default), OpenAI, Groq, Gemini (API + CLI), a local Ollama runtime, the Codex CLI (piggyback on ChatGPT), and the Claude Code CLI (reuse your Claude subscription). An Anthropic profile stub exists in the config for future work but is not wired up yet.

https://github.com/user-attachments/assets/91e888ad-0279-4d84-924b-ba96c0fe43a0

Names and typing speed

qq means quick question. qa means quick agent. Both are easy to type rapidly on QWERTY keyboards with minimal finger movement. That makes interacting with LLMs faster and more natural during real work.

Philosophy

qqqa is deliberately stateless. There is no long running session and no hidden conversation memory stored by the tool. Every run is mostly independent and reproducible. For maintaining a lowkey continuity you can use "include_history": true in the config.json (or choose to use history during the qq --init process).

Why stateless is great: Simple and focused - Unix philosophy applied to LLM tools. Shell friendly - compose with pipes and files instead of interactive chats. Safe by default - qq is read-only and has access to no tools. qa is built with security in mind and requires confirmation before running tools.