Alternatives
Products that do what ShellTalk brings deterministic text-to-bash does
Hi HN! I built a CLI tool called ShellTalk for macOS, Linux, and web (WebAssembly) that maps English text to the corresponding Bash commands. ShellTalk is written in Swift and available under the Apache 2.0 license on GitHub. I was inspired a few weeks ago after reading the Meta-Harness paper and seeing a tool called Hunch that did something similar using the Apple Foundation model. I often forget flag names and orders, but I wanted something that worked consistently. The 3B AFM worked surprisingly well with Hunch, but it felt slow and sometimes slight changes in what I wrote would result in…
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8IW
Hello! This ebook aims to teach Linux command line tools and Shell Scripting for beginner to intermediate level users. The main focus is towards managing your files and performing text processing tasks. Includes plenty of examples, exercises (200+) and solutions. To celebrate my latest ebook release, you can download PDF/EPUB versions of Computing from the Command Line for FREE till 08-Nov-2022: https://learnbyexample.gumroad.com/l/cli_computing (the web version linked as the post url is always free) All books bundle (all my 13 programming ebooks) is $10 (normal…
2022 · learnbyexample.github.io
- 9CT
2019 · github.com
- 10EP
There are easy and there are hard unix shell commands to remember, nobody knows them all. Why not use ChatGPT to translate plain english instructions into executable shell commands. Here are a few examples how `englishell` CLI can be used: $ englishell kill the process that listens to port 8080 -> lsof -i :8080 | awk '{print $2}' | tail -n 1 | xargs kill -9 $ englishell print current git branch -> git branch --show-current $ englishell show the sizes of all folders in parent of the current directory -> du -sh ../* $ englishell how long the system has been running -> uptime $ englishell…
2023 · github.com
- 11UN
Hi HN, I just released a very simple AI Shell / CLI tool that lets you convert natural language directly into executable shell commands. Built with python to simplify terminal workflows and help you quickly run commands without memorizing syntax. It has two main usage modes: One-shot mode: Quickly execute commands using natural language. Example: ai "find all PNG files larger than 5MB" The AI responds with the appropriate command and asks if you want to execute it. Interactive chat mode: Start a terminal chat session with the AI (ai -i) to iteratively build commands or scripts. Some…
2025 · github.com
- 12SB
2020 · github.com
- 13SA
The startup I work for has an internal, bash-based, cli that basically amounts to shared aliases with a common entrypoint. As the number of aliases has grown, I've had a desire to group functionality together in subcommands, add more help strings, and have better tab completion. I know I could convert it to, e.g., a python script, but I was curious what was possible if we continued to use bash. I couldn't find anything that solved those problems without lots of extra machinery. I understand why, shell scripts are generally not long, and focused on a dedicated task; adding cli features to…
Mar 2026 · github.com
- 14TE
Hey everyone, here is an open source project I've been working on to add voice input/output to terminal based coding agents. One thing about the new terminal coding agents I really like is being able to multi-task but right now it's a bit like a Tesla on autopilot needing your hands still on the wheel. You need to be checking often if your input is required or if it's going off the rails. To be able to go fully hands free I wanted to add TTS and ASR. Then I added slack and WhatsApp hooks to TalkiTo as well. It's fully open source with a BYOK philosophy and it's configured to work with…
Nov 2025 · github.com
- 15YA
I was looking for a push-to-talk tool that allows me to just paste my speech transcription automatically into whatever application I'm using. I wasn't able to find anything simple enough that works, so I built my own. For now, it's just a basic CLI that works on Linux only using whisper.cpp. It is incredibly simple. You hold down the buttons, say stuff, release and then it will pipe the transcription lines to stdout. I'm using it to write this comment :)
Sep 2025 · github.com
- 16LC
2015 · github.com
- 17IW
Shelon: https://github.com/housni/sheldon It's not a framework, it's a library. It attempts to mimic function names in Python. Most functions work in Bash 4.3+ but there are those that work on older versions. The 'help' target in Makefile is on crack! Check the issues in that repo for upcoming features. Useful for DevOps Engineers or anyone who has to write Bash scripts.
2018
- 18LF
Hey HN, I built SWE-Kit, LLM toolkit (Function callable tools) which makes building agents specialised in coding like Devin very easy. I noticed a typical pattern while building local agents: creating & perfecting LLM tools to interact with system or codebase was the repeated and time-consuming. We created a layer that simplifies building agents that can interact with code, file system, git, shell and allows you to quickly solve for a wide variety of coding agent use cases. Aren’t there open coding agents already? Well, yes, but most folks would want to solve their specific use case like a…
2024 · swekit.dev
- 19AT
2016 · github.com
- 20CA
Fun agent I've been playing with - the idea is it only has access to a bash tool, and it's directed to create CLIs for use (with additional direction to make the CLIs composable, follow the Unix philosophy, etc). It persists these CLIs and knowledge about them get injected into the system prompt dynamically, so each time it runs it gets access to a larger and larger toolset of composable CLIs. One interesting dynamic that's emerged from this is I've started using these CLIs myself since they're the same interface for the agent or for me, and it's turned into kind of non-chat channel to…
Jan 2026 · github.com
- 21CA
2023 · github.com
- 22NT
I built a CLI tool that turns codebases and PRs into diagrams so you can quickly understand how things fit together. Originally made it because I couldn't follow my own AI-generated repos. Just shipped a big update: - Switched from D2 to Mermaid for rendering - Tree-sitter AST parsing + agentic flow instead of raw LLM calls. ~50x faster. - Works on any GitHub repo or PR, not just local - Dropped the web frontend, it's just a CLI now - Published as a pip package Still a ton to improve and I'm building fast. Feedback, issues, PRs all welcome.
Feb 2026 · github.com
- 23SG
2016 · github.com
- 24OW
I built Open WhisperScribe after struggling with the complexity, paywalls, or limitations of most speech-to-text tools for macOS and elsewhere. My main requirements were: Simple, <5-min setup Runs fully offline, locally (no data leaves your machine) Works seamlessly in any app — just press a hotkey, speak, and your words appear where your cursor is (code editors, terminal, you name it) Fast and distraction-free It uses OpenAI’s Whisper model under the hood, but wraps it in a lightweight CLI tool that sits quietly in the background. The project is open source (Apache 2.0). Setup is a single…
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →