Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

simonwillison.net

Post reply on HN
Print view View original

11–20 of 178 posts

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#11

Post by th0ma5 »

dang wrote: post #5
th0ma5 wrote: post #4

[flagged]

Comments like this break both the HN guidelines ( https://news.ycombinator.com/newsguidelines.html ) and the Show HN guidelines ( https://news.ycombinator.com/showhn.html ). Can you please review those and please not post like this?

I don't know the context that could be cordial when there is so much outright dishonesty about the state of LLM uptake. Can we have some guidance about how to call out bullshit? I know that the fake it to you make it or sell the shovels to the gold rush people are staples on here, but I don't what to do with a technology that is purely for that and seemingly for nothing else. Why do all of the breathless pro-LLM posts get pushed to the top of every LLM story, and you have to go to the second comment aways to see the avalanche of people calling bullshit? Thank you for your time moderating, it would be helpful to understand the guidance in face of the brigrading on here.

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#12

Post by simonw »

sorenjan wrote: post #8

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 installed plugins are lost.

Sorry about that! Presumably you're updating via Homebrew? That blows away your virtual environment, hence why the plugins all go missing.

I have an idea to fix that by writing a 'plugins.txt' file somewhere with all of your installed plugins and then re-installing any that go missing - issue for that is here: https://github.com/simonw/llm/issues/575

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#14

Post by simonw »

oliviergg wrote: post #7

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 released version 0.26 alpha, I’ve been trying to create a plugin to interact with a some MCP server, but it’s a bit too challenging for me. So far, I’ve managed to connect and dynamically retrieve and use tools, but I’m not yet able to pass param…

Yeah I had a bit of an experiment with MCP this morning, to see if I could get a quick plugin demo out for it. It's a bit tricky! The official mcp Python library really wants you to run asyncio and connect to the server and introspect the available tools.

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#15

Post by simonw »

behnamoh wrote: post #3

unrelated note: your blog is nice and I've been following you for a while, but as a quick suggestion: could you make the code blocks (inline or not) highlighted and more visible?

I have syntax highlighting for blocks of Python code - e.g. this one https://simonwillison.net/2025/May/27/llm-tools/#tools-in-th... - is that not visible enough?

This post has an unusually large number of code blocks without syntax highlighting since they're copy-pasted outputs from the debug tool which isn't in any formal syntax.

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#16

Post by th0ma5 »

simonw wrote: post #10
behnamoh wrote: post #2

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 that others don't? am I missing something?

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 prompts and responses to its SQLite database. This makes it fantastic for recording experiments with different models over time. The ability to pipe files and other program outputs into an LLM is wildly useful. A few examples: llm -f code.py -s '…

"LLM was used to find" is not what they did

> had I used o3 to find and fix the original vulnerability I would have, in theory [...]

they ran a scenario that they thought could have lead to finding it, which is pretty much not what you said. We don't know how much their foreshadowing crept into their LLM context, and even the article says it was also sort of chance. Please be more precise and don't give into these false beliefs of productivity. Not yet at least.

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#17

Post by th0ma5 »

dang wrote: post #5
th0ma5 wrote: post #4

[flagged]

Comments like this break both the HN guidelines ( https://news.ycombinator.com/newsguidelines.html ) and the Show HN guidelines ( https://news.ycombinator.com/showhn.html ). Can you please review those and please not post like this?

I also added another reply to a false assertion by the OP here in this thread. Is that better ? It takes a long time to research all these falsehoods that are leading to the hype.

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#18

Post by simonw »

th0ma5 wrote: post #16
simonw wrote: post #10

Earlier quoted context omitted.

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 prompts and responses to its SQLite database. This makes it fantastic for recording experiments with different models over time. The ability to pipe files and other program outputs into an LLM is wildly useful. A few examples: llm -f code.py -s '…

"LLM was used to find" is not what they did > had I used o3 to find and fix the original vulnerability I would have, in theory [...] they ran a scenario that they thought could have lead to finding it, which is pretty much not what you said. We don't know how much their foreshadowing crept into their LLM context, and even the article says it was also sort of chance. Please be more precise and don't give into these fa…

I said "LLM was also used recently in that..." which is entirely true. They used my LLM CLI tool as part of the work they described in that post.

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#19

Post by dr_kretyn »

Maybe a small plug of own similar library: terminal-agent (https://github.com/laszukdawid/terminal-agent) which also supports tools and even MCP. There's a limited agentic capability but needs some polishing. Only once I made some progress on own app I learned about this `llm` CLI. Though that one more won't harm.

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#20

Post by Uehreka »

th0ma5 wrote: post #9
simonw wrote: post #6

Earlier quoted context omitted.

"don't actually do anything with this stuff" - https://github.com/simonw/llm/compare/0.25...0.26 138 commits to implement this new feature.

[flagged]

That’s what his llm CLI is? I’ve been waiting for this release so I can take my existing notes on best practices coding with LLMs (which I’ve been doing for both work projects and side projects) and try some experiments with rolling a coding agent myself instead of using Claude Code or VS Code’s Agent mode. If it works well then other folks on my team might switch to it too.

I don’t get where you get the idea that people aren’t actually using this stuff and being productive.

Post reply on HN