simonwillison.net

AI

llm cli

SHOW HN2025

Legend

simonwillison.net

My LLM CLI tool can run tools now, from Python code or plugins

simonwillison.net

#llm cli#tool calling#llm plugins#python llm

529points
165comments
#61of 3,837 in 2025
Top 2%of 2025 by points

How HN took it

MixedNo clear lean

24 positive, 29 neutral or asking, 1 mixed, 7 critical, out of 61 comments about the project. Thread score +0.24.

Idea: 5 for, 2 againstExecution: 3 for, 1 againstDocs: 3 for, 0 againstDesign: 2 for, 1 againstPerformance: 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 research tool with logging of prompts and responses

    From 2 comments
    • I find it extremely useful as a research tool. It can talk to probably over 100 models at this point, providing a single interface to all of them and logging full details of…
      simonw on HN
    • Great work Simon! I use your tool daily. Pipes and easy model switching for local (ollama) and remote makes this very easy to work with.
      hanatanaka1984 on HN
  • Simple plugin and Python API for tool calling

    From 2 comments
    • Thanks for making this. I used it (0.26a0) last week to create a demo for a customer-facing chatbot using proprietary data. The key elements I had to write: - The system prompt -…
      rahimnathwani on HN
    • This is great, and a feature I was hoping for, for a long time. At this point I would have expected something mcp or openapi based but probably is simpler and more flexible this…
      samuel on HN

Objections

  • Tool calling risks footguns like unintended actions

    From 2 comments
    • This greatly opens up the risk of footguns. The doc [1] warns about prompt injection, but I think a more likely scenario is self-inflicted harm. For instance, you give a tool…
      tantalor on HN
    • Ok this is great and perfect timing -- I've been playing around with Warp (the terminal) and while I love the idea of their terminal-based "agent" (eg tool loop), I don't love…
      nlh on HN
  • Updating via Homebrew removes installed plugins

    From 1 comment
    • Every time I update llm I have to reinstall all plugins, like gemini and ollama. My Gemini key is still saved, as are my aliases for my ollama models, so I don't get why the…
      sorenjan on HN
  • Slow startup from expensive plugin imports

    From 1 comment
    • Simon thank you so much for this tool! I use it daily now since charmbraclet’s Mods[0] doesn’t support anthropics models. And now with tool calling it’ll be even more useful. I…
      roxolotl on HN

Requests

  • Per-call permission prompts for tools

    From 1 comment
    • Ok this is great and perfect timing -- I've been playing around with Warp (the terminal) and while I love the idea of their terminal-based "agent" (eg tool loop), I don't love…
      nlh on HN
  • Better tutorial and documentation

    From 1 comment
    • I really need to put together a better tutorial - there's a TON of documentation but it's scattered across a bunch of different places: - The official docs:…
      simonw on HN
  • MCP support

    From 1 comment
    • Thank you for this release. I believe your library is a key component to unlocking the potential of LLMs without the limitations/restricitions of existing clients. Since you…
      oliviergg on HN

Questions

  • How does this differ from other CLI tools and LangChain tool calling?

    From 2 comments
    • what are the use cases for llm, the CLI tool? I keep finding tgpt or the bulletin AI features of iTerm2 sufficient for quick shell scripting. does llm have any special features…
      behnamoh on HN
    • How does this differ from langchain's tool calling?
      a_bonobo on HN
  • Whether tool calls work reliably across models

    From 1 comment
    • Have you guys had luck with tool calls? I made a simple assistant with access to my calendar, and most models fail to call the tool to add calendar events. GPT-4.1 also regularly…
      stavros on HN

Alternatives named

  • LangChain

    From 1 comment
  • tgpt and iTerm2 AI features

    From 1 comment
    • what are the use cases for llm, the CLI tool? I keep finding tgpt or the bulletin AI features of iTerm2 sufficient for quick shell scripting. does llm have any special features…
      behnamoh on HN
  • Warp terminal agent

    From 1 comment
    • Ok this is great and perfect timing -- I've been playing around with Warp (the terminal) and while I love the idea of their terminal-based "agent" (eg tool loop), I don't love…
      nlh on HN
  • Claude Code

    From 1 comment
    • @simonw, how much have you used Claude code? I'm wondering if it makes sense to use Claude code as the main driver, but have crafted specialized "llm" based tools for Claude to…
      jasonriddle 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/44110584)