promptcmd

Hey HN! I am an avid terminal user who sees value in prompts executing like, and having the UX of native CLI programs, i.e., with --help, argument parsing, stdin/stdout, and composability via pipes. So I came up with a tool (not vibe-coded, built over 4+ months) where you write a .prompt file with a template (Handlebars-style), enable it with promptctl enable, and it becomes a command you can run in your terminal. For example: So I built a tool where you write a .prompt file with a template (Handlebars-style), enable it with `promptctl enable`, and it becomes a command you can run: cat compose.yml | askdocker "add a load balancer" ai-analyze-logs --container nginx It supports multiple providers (Anthropic, OpenAI, Ollama, OpenRouter, Google), load balancing across them, response caching, and custom model "variants" with different sys

Instead of giving LLM tools SSH access or installing them on a server, the following command: $ promptctl ssh user@server makes a set of locally defined prompt templates "magically" appear within the remote shell as executable command line programs. For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can: $ promptctl ssh user@host # Now on remote host $ llm-analyze-config /etc/nginx.conf $ cat docker-compose.yml | askai "add a load balancer" the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though they're invoked remotely) via the llm of my choosing. This way LLM tools are never granted SSH access to the server, and nothing needs to be installed to the server. In fact, the server does not even need outbound internet connections to b

Hi HN, This is a tool I've worked on the past few months (not vibe-coded). Instead of giving LLM tools SSH access or installing them on a server, the following command: $ promptctl ssh user@server makes a set of locally defined prompts "magically" appear within the remote shell as executable command line programs. For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can: $ promptctl ssh user@host # Now on remote host $ llm-analyze-config /etc/nginx.conf $ cat docker-compose.yml | askai "add a load balancer" the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though they're invoked remotely) via the llm of my choosing. This way LLM tools are never granted SSH access to the server, and nothing needs to be installed to the server. In fact

Hi HN, This is a tool I've worked on the past few months. Instead of giving LLM tools SSH access or installing them on a server, the following command: $ promptctl ssh user@server makes a set of locally defined prompts "magically" appear within the remote shell as executable command line programs. For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can: $ promptctl ssh user@host # Now on remote host $ llm-analyze-config /etc/nginx.conf $ cat docker-compose.yml | askai "add a load balancer" the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though they're invoked remotely) via the llm of my choosing. This way LLM tools are never granted SSH access to the server, and nothing needs to be installed to the server. In fact, the server does

Instead of giving LLM tools SSH access or installing them on a server, the following command: $ promptctl ssh user@server makes a set of locally defined prompts "magically" appear within the remote shell as executable command line programs. For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can: $ promptctl ssh user@host # Now on remote host $ llm-analyze-config /etc/nginx.conf $ cat docker-compose.yml | askai "add a load balancer" the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though they're invoked remotely) via the llm of my choosing. This way LLM tools are never granted SSH access to the server, and nothing needs to be installed to the server. In fact, the server does not even need outbound internet connections to be enabled

Instead of giving LLM tools SSH access or installing them on a server, the following command: $ promptctl ssh user@server makes a set of locally defined prompts "magically" appear within the remote shell as executable command line programs. For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can: $ promptctl ssh user@host # Now on remote host $ llm-analyze-config /etc/nginx.conf $ cat docker-compose.yml | askai "add a load balancer" the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though they're invoked remotely) via the llm of my choosing. This way LLM tools are never granted SSH access to the server, and nothing needs to be installed to the server. In fact, the server does not even need outbound internet connections to be enabled

Instead of giving LLM tools SSH access or installing them on a server, the following command: $ promptctl ssh user@server makes a set of locally defined prompts "magically" appear within the remote shell as executable command line programs. For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can: $ promptctl ssh user@host # Now on remote host $ llm-analyze-config /etc/nginx.conf $ cat docker-compose.yml | askai "add a load balancer" the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though they're invoked remotely) via the llm of my choosing. This way LLM tools are never granted SSH access to the server, and nothing needs to be installed to the server. In fact, the server does not even need outbound internet connections to be enabled

Instead of giving LLM tools SSH access or installing them on a server, the following command: $ promptctl ssh user@server makes a set of locally defined prompts "magically" appear within the remote shell as executable command line programs. For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can: # on remote host $ llm-analyze-config /etc/nginx.conf $ cat docker-compose.yml | askai "add a load balancer" the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though they're invoked remotely) via the llm of my choosing. This way LLM tools are never granted SSH access to the server, and nothing needs to be installed to the server. Github: https://github.com/tgalal/promptcmd/ Docs: https://docs.promptcmd.sh/

I wanted a "seamless" way for executing llm prompts in my terminal for recurring tasks, and came up with this: http://github.com/tgalal/promptcmd The cool thing about it is that it also works over remote ssh shells, so quite handy in managing my homelab.

Instead of giving LLM tools SSH access or installing them on a server, the following command: $ promptctl ssh user@server makes a set of locally defined prompts "magically" appear within the remote shell as executable command line programs. For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can: # on remote host $ llm-analyze-config /etc/nginx.conf $ cat docker-compose.yml | askai "add a load balancer" the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though they're invoked remotely) via the llm of my choosing. This way LLM tools are never granted SSH access to the server, and nothing needs to be installed to the server. Github: https://github.com/tgalal/promptcmd/ Docs: https://docs.promptcmd.sh/

Instead of giving LLM tools SSH access or installing them on a server, the following: promptctl ssh user@server makes a set of locally defined prompts "appear" within the remote shell as executable command line programs. For example: # on remote host analyze-config --help Usage: analyze-config [OPTIONS] --path <path> Prompt inputs: --all --path <path> --opt --syntax --sec would render and execute the following prompt: You are an expert sysadmin and security auditor analyzing the configuration file {{path}}, with contents: {{cat path}} Identify: {{#if (or all syntax) }}- Syntax Problems{{/if}} {{#if (or all sec) }}- Misconfigurations and security risks{{/if}} {{#if (or all opt) }}- Optimizations{{/if}} For each finding,

This is an example tool I created using my tool (promptcmd) for turning prompts into "native-looking" executables: Usage: bashme_a_script_that [OPTIONS] <query>... Prompt inputs: --stdin accept stdin input <query>... positional query. Can be spaced and with/without quotes It makes use of caching responses: if I review the generated script and it looks good (or incomprehensible and I'm in YOLO mood), I run the command again and pipe directly into bash. It'll use the reviewed response instead of generating a new one. Would love to get feedback or ideas for promptcmd: Github: https://github.com/tgalal/promptcmd/ Documentation: https://docs.promptcmd.sh/ Examples: https://promptcmd.sh/lib/

Lately I've seen several projects for templating and executing prompts. However they all go along the lines of $ executor prompt_file_or_name which didn't exactly fit my "taste". I figured one could use the same trick like busybox, where you can detect if your binary is being executed via a different name (symlink). The symlink name is treated as the promptname, and arguments are generated from a schema defined in the prompt template. So now instead of: # Using https://github.com/chr15m/runprompt echo '{"words": 300, "text": "some long text"}' | ./runprompt summarize.prompt # Or using https://github.com/simonw/llm echo "some long text" | llm -t summarize -p words 300 You get: echo "some long text" | summarize --words 300 And of course with documented arguments and so on: summarize --help Usage: summarize [OPTIONS] --