nsh sits in your shell. Ask questions with ?, and it investigates, asks clarifying questions, runs safe intermediate steps, and verifies outcomes before finishing. Dangerous commands are always gated.
nsh reads your scrollback, knows your project, and remembers history. It understands context without explanation.
nsh chains investigation, execution, and verification. Safe intermediate steps continue automatically; dangerous commands always require explicit confirmation.
Works with OpenRouter, Anthropic, OpenAI, Gemini, or local models via Ollama. Bring your own key.
Secrets are redacted locally. Dangerous commands require confirmation. Sensitive paths blocked.
Custom skills, MCP tool servers, persistent memory, and project-local configuration.
BSD 3-Clause licensed. All data local in SQLite. No telemetry. No vendor lock-in.
Type ? followed by your natural language question right in your terminal.
nsh analyzes your shell history, runs safe checks, reads relevant files, and asks you to disambiguate when names are ambiguous.
nsh executes safe intermediate steps, checks results, recovers from errors, and only finishes when the task is actually complete.
Works with your existing shell on macOS, Linux, FreeBSD, and Windows.