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

Gemini CLI

blog.google

Post reply on HN
Print view View original

801–810 of 820 posts

Re: Gemini CLI

#801

Post by ericb »

_ryanjsalva wrote: post #57
elashri wrote: post #52

Earlier quoted context omitted.

Hi, Thanks for this work. currently it seems these are the CLI tools available. Is it possible to extend or actually disable some of these tools (for various reasons)? > Available Gemini CLI tools: - ReadFolder - ReadFile - SearchText - FindFiles - Edit - WriteFile - WebFetch - ReadManyFiles - Shell - Save Memory - GoogleSearch

I also work on the product. You can extend the tools with MCP. https://github.com/google-gemini/gemini-cli/blob/main/docs/t...

>gemini -p "Say hello"

  Says hello, and just returns right away.
The gemini doc for -p says "Prompt. Appended to input on stdin (if any)." So it doesn't follow the doc.

gemini "Say hello"

  Fails as it doesn't take any arguments.
For comparison, claude lets you pass the prompt as a positional argument, but it does append it to the prompt and then gives you a running session. That's what I'd want for my use-case.

Re: Gemini CLI

#802

Post by ericb »

cperry wrote: post #744
akrauss wrote: post #705

Earlier quoted context omitted.

There is one feature in Claude Code which is often overlooked and I haven't seen it in any of the other agentic tools: There is a tool called "sub-agent", which creates a fresh context windows in which the model can independently work on a clearly defined sub-task. This effectively turns Claude Code from a single-agent model to a hierarchical multi-agent model (I am not sure if the hierarchy goes to depths >2). I won…

conscious decision not to include it mostly to cut a release we could ship to land yesterday ;) various forms of this are being discussed, this commentary is helpful thanks!

Injecting ENV variables into the template would be super useful.

Re: Gemini CLI

#803

Post by phonon »

vessenes wrote: post #798
phonon wrote: post #603

Earlier quoted context omitted.

What's wrong with https://aistudio.google.com/app/u/1/apikey ? https://ai.google.dev/gemini-api/docs/api-key?authuser=1

Well, originally what was wrong was that non-vertex customers got much lower limits and about twice the time to first token as vertex customers. So I used a vertex key setup. However, the cli had me in auth hell trying to connect up with vertex. Like literal spinning. So, thank you. I wiped my vertex environment variables and upped my gemini key level, and it mostly works now.

Glad to help! Also, in case it matters, the old "google-generativeai" libraries have now been replaced with "google-genai".

Re: Gemini CLI

#804

Post by krzyk »

nprateem wrote: post #619
8n4vidtmkvmk wrote: post #572

Earlier quoted context omitted.

O3 does, no? 2.5 Pro is a thinking model. Try flash if you want faster responses

No. We're not talking a few useful comments, but verbosity where typically the number of comments exceeds the actual code written. It must think we're all stupid or it's documenting a tutorial. Telling it not to has no effect.

Maybe you hit a specific use case where the LLM part turns into its roots?

I had a somehos similar problem with Claude 3.7, where I had a class named "Workflow" and it got nuts, producing code/comments I didn't ask for, all related to some "workflow" that it tried to replicate and not my code, it was strange.

Re: Gemini CLI

#805

Post by sometimes_all »

rvnx wrote: post #616
scoopdewoop wrote: post #295

Earlier quoted context omitted.

It is bold to assume these products will even exist in a year

This is also tied to the internal promotion system within Google; you get promoted and rewarded for launching new products. Way less for maintenance.

Yes this is a well-known trope in HN about promotion-oriented launches, but this is just pure lack of proper messaging. I had a chat with one of Google's representatives, and they keep on saying "they do not have any information on this as of now".

This is less about internal systems and more about either incompetence or active sabotage.

Re: Gemini CLI

#806

Post by rs186 »

frollogaston wrote: post #770
rs186 wrote: post #149

Earlier quoted context omitted.

Eh, I can't see how your comment is relevant ti the parent thread. Creating a CLI in Go is barely more complicated than JS. Rust, probably, but people aren't asking for that.

They wrote the CLI "GUI" in React using ink, which is all JS-only. I don't know what the Golang way of doing this would be, but maybe it's harder if you want the same result.

There are many GUI building libraries in Go. Sure, you wouldn't be writing JSX (and I agree it's an interesting idea), but it doesn't mean it's more any work to get things rendered in a terminal with other approaches, especially with these AI assistants to help you finish the boring parts.

Re: Gemini CLI

#807

Post by irthomasthomas »

Game_Ender wrote: post #687
irthomasthomas wrote: post #326

Earlier quoted context omitted.

If you uv install llm Then grab my shelllm scripts github.com/irthomasthomas/shelllm and source them in your terminal then you can use premade prompt functions like shelp "what's a nm and grep command to find this symbol in these 3 folders" -m gemini-pro There's also wrappers that place the command directly in your terminal prompt if you run shelp-c

The link you have posted 404’s and I could seem to find a command like that in your repos. Can you be more specific?

Sorry, the function is in here and it's called shelp https://github.com/irthomasthomas/shelllm.sh/blob/main/shell...

Re: Gemini CLI

#808

Post by seunosewa »

breakingcups wrote: post #724
seunosewa wrote: post #697

Earlier quoted context omitted.

Put in the file: Instructions for Claude: - ... - ... Instructions for Gemini: - ... - ...

But then the irrelevant instructions are just cluttering the context.

Most of the instructions will be suitable for all the models. Only a few will be model-specific.

Re: Gemini CLI

#810

Post by frabcus »

cperry wrote: post #488
atonse wrote: post #311

This is all very cool, but I hate to be the "look at the shiny lights" guy... How did they do that pretty "GEMINI" gradient in the terminal? is that a thing we can do nowadays? It doesn't seem to be some blocky gradient where each character is a different color. It's a true gradient. (yes I'm aware this is likely a total clone of claude code, but still am curious about the gradient)

we went through several versions of this, it was the second most fun part after authoring the witty loading phrases.

For the record, I find the witty loading phrases a real turn-off. It makes me feel like I don't know what it is doing, and it is being patronising.
Post reply on HN