Savvy – Create, Share and Run Runbooks from your Terminal
Savvy's CLI allows you to create, share, and run runbooks from your terminal. Savvy(getsavvy.so) natively integrates with modern LLMs and reduces the time to create a great runbook from minutes and hours to seconds. Savvy supports creating runbooks entirely with AI(savvy ask) or a human in the loop(savvy record.) Savvy Ask: Generate entire runbooks or a single command using natural language. Savvy Record: This creates a new subshell that automatically expands all aliases before recording commands locally. These commands are then sent to an LLM, which generates the first version of your…
In plain words
Savvy is a command-line tool that helps users create, share, and run runbooks from the terminal. It integrates with large language models to speed up runbook creation through two methods: "Savvy Ask" generates runbooks from natural language descriptions, while "Savvy Record" captures commands from shell history and uses AI to create structured runbooks. Users can keep runbooks private or share them with teammates via links or export them as markdown. The tool is designed for developers and teams who need to document and automate repetitive terminal workflows.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Savvy's CLI allows you to create, share, and run runbooks from your terminal. Savvy(getsavvy.so) natively integrates with modern LLMs and reduces the time to create a great runbook from minutes and hours to seconds. Savvy supports creating runbooks entirely with AI(savvy ask) or a human in the loop(savvy record.) Savvy Ask: Generate entire runbooks or a single command using natural language. Savvy Record: This creates a new subshell that automatically expands all aliases before recording commands locally. These commands are then sent to an LLM, which generates the first version of your runbook. Savvy Record History: This command allows you to go back in time and select commands from your recent shell history. There's no need to repeat the work you've already done. Runbooks are private by default, but you can share them with your team using a link(for now) or export them to markdown. Savvy Explain: Savvy explain generates a simple and easy-to-understand explanation for any command or error message before you can say RTFM! Savvy Run: Use `savvy run` to search and run runbooks right from your terminal. Once you select a runbook, Savvy automatically fills in the next command to execute. Just press enter to run it. Savvy's README has more details and demos for everything I just mentioned. Savvy's free, and anyone can try it out today. Install Savvy by running: curl -fsSL https://install.getsavvy.so | sh If you try Savvy, I'd love your feedback on the product.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
