Get the latest tech news
Show HN: Llm2sh – Translate plain-language requests into shell commands
Ask GPT to run a command. Contribute to randombk/llm2sh development by creating an account on GitHub.
llm2sh is a command-line utility that leverages Large Language Models (LLMs) to translate plain-language requests into shell commands. Model NameProviderAccuracyCostNotes local N/A¯\(ツ)/¯ FREE Needs local OpenAI API compatible LLM Api Endpoint (i.e. llama.cpp) groq-llama3-70b Groq🧠🧠🧠 FREE(with rate limits) Blazing fast; recommended groq-llama3-8b Groq🧠🧠 FREE(with rate limits) Blazing fast groq-mixtral-8x7b Groq🧠 FREE(with rate limits) Blazing fast groq-gemma-7b Groq🧠 FREE(with rate limits) Blazing fast gpt-4o OpenAI🧠🧠💲💲💲Default model gpt-4-turbo OpenAI🧠🧠🧠💲💲💲💲 gpt-3.5-turbo-instruct OpenAI🧠🧠💲💲 claude-3-opus Claude🧠🧠🧠🧠💲💲💲💲Fairly slow (>10s) claude-3-sonnet Claude🧠🧠🧠💲💲💲Somewhat slow (~5s) claude-3-haiku Claude🧠💲💲 ✅ Support multiple LLMs for command generation ⬜ User-customizable system prompts ⬜ Integrate with tool calling for more complex commands ⬜ More complex RAG for efficiently providing relevant context to the LLM ⬜ Better support for executing complex interactive commands ⬜ Interactive configuration & setup via the command line To help LLMs generate better commands, llm2sh may send the following information as part of the LLM prompt in addition to the user's request:
Or read this on Hacker News