Show HN: Smartly – Plain English to shell commands, with GNU/BSD awareness

Developer Rizwan Reza released Smartly, a CLI tool that sends one plain English sentence to an LLM, validates the reply is a single shell command line, and runs it, with install via `brew install rizwanreza/tap/smartly` or `go install github.com/rizwanreza/smartly-cli/cmd/smartly@latest`. Smartly detects whether tools like `sed`, `date` and `stat` are GNU or BSD on the host and writes matching flags, sends a capped directory listing plus git branch, status and worktrees as context, and supports four providers (anthropic, openai, claude-cli, codex-cli) and four execution modes (auto, confirm, confirm-destructive, --dry-run). Auto-run is the default and executes generated commands immediately with no confirmation, including destructive ones, so the tool's own documentation recommends switching to confirm or confirm-destructive on machines where a wrong `rm` is costly.

Tell your shell what you mean. You know what. smartly knows how. smartly sends one plain English sentence to an LLM, validates the reply is a single shell command line, and runs it. For people who know what they want to do and would rather not remember the exact flags. Install brew install rizwanreza/tap/smartly go install github.com/rizwanreza/smartly-cli/cmd/smartly@latest Then run smartly onboard to pick a provider, a model and an execution mode. The transform Say the outcome. Get the command. What it does Commands without the ceremony. - english → command - One sentence in, one command outDescribe the result. smartly returns a single executable shell command — pipes, && and redirects allowed, multi-step scripts never. - macos + linux - Knows which userland it is onIt checks whether sed , date , stat and friends are GNU or BSD on your machine — a Mac with Homebrew coreutils has both — and writes flags that work with the ones you have: sed -i '' for BSD, date -d for GNU. - dir + git - Reads the roomBy default it sends a capped directory listing plus your git branch, status and worktrees, so “all worktrees except main” resolves against what is actually there. - four providers - Your model, your billingAnthropic and OpenAI by API key, or your own logged-in claude / codex CLI session if you already pay for a subscription. - four ways to run - Four ways to run it auto runs the command immediately and is the default. confirm asks y/N every time, confirm-destructive asks on anything it doesn’t recognise as safe, and --dry-run prints the command and runs nothing. - learn mode - Shows how the command works --learn prints the command, then breaks it down piece by piece: each flag, pipe and argument with what it does, colour-matched to the command above. Nothing runs. Before you install it Auto-run is the default. smartly generates a command and runs it immediately, with no confirmation prompt — including when that command is destructive. Under auto nothing inspects what the command does; the only check is that the model returned exactly one clean command line. That is the product working as intended, and it is the setting most worth reconsidering on a machine where a wrong rm costs you something. Three ways to change it: confirm Ask me every time Prints the command and waits for y/N . Reads /dev/tty directly, and fails closed when there is no terminal. ~/.config/smartly/config.yaml execution: mode: confirm confirm-destructive Ask me when it is not clearly safe A local classifier reads the generated command and asks on anything it doesn’t recognise as safe — destructive or unrecognised alike. A best-effort seatbelt, not a sandbox: to see every command, use confirm . ~/.config/smartly/config.yaml execution: mode: confirm-destructive --dry-run Just show me Prints the command and does nothing else. The right flag for a phrasing you are not sure about yet. smartly --dry-run remove every merged branch Providers Four backends. Bring an API key or your existing CLI login. anthropic and openai call an API with your own key. claude-cli and codex-cli shell out to a CLI you are already logged into — slower, but no second bill. And openai speaks to any OpenAI-compatible endpoint, including a local vLLM, Ollama or LM Studio. | Provider | Authentication | Worth knowing | |---|---|---| | anthropic | ANTHROPIC API KEY | The default. Nothing to configure beyond the key. | | openai | OPENAI API KEY | Ships no default model — set providers.openai.model yourself. | | claude-cli | Your logged-in claude session | No API key: uses your Claude subscription. No tool access at all. | | codex-cli | Your logged-in codex session | No API key: uses your ChatGPT subscription. Runs --sandbox read-only. | Describe the result. Skip the flag archaeology. brew install rizwanreza/tap/smartly go install github.com/rizwanreza/smartly-cli/cmd/smartly@latest