Magic-cli

Dev tools

command line assistant

SHOW HN2024

158points
94comments
#530of 3,515 in 2024
Top 16%of 2024 by points

How HN took it

CuriousMostly questions and neutral comments

3 positive, 15 neutral or asking, 0 mixed, 11 critical, out of 29 comments about the project. Thread score -0.24.

Execution: 0 for, 4 againstDesign: 1 for, 2 againstIdea: 1 for, 2 againstDocs: 0 for, 1 againstPrivacy: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Useful, similar tools praised for workflow

    From 2 comments
    • This is nice. I've been taking Termium[0] for a spin and it's been pretty great for the most part, but the Rumsfeld-complete always-on autosuggest/copilot UX they're aiming for…
      boomskats on HN
    • I'll bet this was a lot of fun to make. Very cool project. Was there any particular motive for building your own over using something that's been around a bit longer like aichat?…
      tiberriver256 on HN

Objections

  • Default unsafe-execution mode is dangerous

    From 3 comments
    • Default mode should probably not be “unsafe-execution” but instead should be “clipboard”. Make people turn on the unsafe mode.
      Carrok on HN
    • ``` suggest.mode: The mode to use for suggesting commands. Supported values: "clipboard" (copying command to clipboard), "unsafe-execution" (executing in the current shell…
      imp0cat on HN
    • I have to agree, this to me seems like a great in theory but questionable in practice. We know how much damage a cli can do, they often don't have the protections in place most…
      nerdjon on HN
  • Slow output because not streaming

    From 1 comment
    • It isn’t streaming the ollama output so it feels slow (~3 words/second on a 3090 with the defaults). Using ollama directly streams within a second and you can kill it early. I…
      deckar01 on HN
  • Too complex for what it does

    From 1 comment
    • Can I ask why it's so complicated? I made something similar about a year ago and it's less that 150 lines of Python. Gives you an explanation, option to run it with/without sudo,…
      bongodongobob on HN

Requests

  • Make clipboard the default mode

    From 1 comment
    • Default mode should probably not be “unsafe-execution” but instead should be “clipboard”. Make people turn on the unsafe mode.
      Carrok on HN
  • Streaming output

    From 2 comments
    • It isn’t streaming the ollama output so it feels slow (~3 words/second on a 3090 with the defaults). Using ollama directly streams within a second and you can kill it early. I…
      deckar01 on HN
    • It's currently set not to stream (https://github.com/guywaldman/magic-cli/blob/4d4dca034063aa6433ebaadcbdb7cc192f55c05c/src/llm/ollama/ollama_llm.rs#L55C13-L55C19). The…
      guywald on HN

Questions

  • How does it compare to existing tools like aichat or llm

    From 2 comments
    • Neat. How does it compare to https://llm.datasette.io/en/stable/ ?
      ano-ther on HN
    • I'll bet this was a lot of fun to make. Very cool project. Was there any particular motive for building your own over using something that's been around a bit longer like aichat?…
      tiberriver256 on HN
  • How is the latency

    From 1 comment

Alternatives named

  • aichat

    From 1 comment
    • I'll bet this was a lot of fun to make. Very cool project. Was there any particular motive for building your own over using something that's been around a bit longer like aichat?…
      tiberriver256 on HN
  • llm-cmd

    From 1 comment
  • zsh_codex

    From 1 comment
    • I've been using https://github.com/tom-doerr/zsh_codex with gpt4-o and it saves a lot of strokes as compared to github copilot cli to query, since I just have to press ctrl-x in…
      pcwelder on HN
  • please-cli

    From 1 comment
  • open-interpreter

    From 1 comment
    • https://github.com/KillianLucas/open-interpreter/ is my preferred implementation of approximately the same thing
      fragmede on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/40980715)