CLI that runs an LLM as a shell command for scripts, refactors, and answers.
Point the base URL at Ollama or LocalAI to keep prompts local.
shell_gpt is a CLI that turns an LLM into a shell command: generate, explain, and execute from one prompt. It talks to any OpenAI-style endpoint, including a local runner you point it at. It is not a chat UI.
shell commands · code generation · reusable prompts · local endpoints