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

151–160 of 820 posts

Re: Gemini CLI

#151

Post by silverlake »

_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...

I tried to get Gemini CLI to update itself using the MCP settings for Claude. It went off the rails. I then fed it the link you provided and it correctly updates it's settings file. You might mention the settings.json file in the README.

Re: Gemini CLI

#152

Post by leumon »

barbazoo wrote: post #103

> To use Gemini CLI free-of-charge, simply login with a personal Google account to get a free Gemini Code Assist license. That free license gets you access to Gemini 2.5 Pro and its massive 1 million token context window. To ensure you rarely, if ever, hit a limit during this preview, we offer the industry’s largest allowance: 60 model requests per minute and 1,000 requests per day at no charge. If it sounds too good…

My guess: So that they can get more training data to improve their models which will eventually be subscription only.

Re: Gemini CLI

#153

Post by cperry »

bsenftner wrote: post #148
cperry wrote: post #41

Hi - I work on this. Uptake is a steep curve right now, spare a thought for the TPUs today. Appreciate all the takes so far, the team is reading this thread for feedback. Feel free to pile on with bugs or feature requests we'll all be reading.

Thank you for your work on this. I spent the afternoon yesterday trying to convert an algorithm written in ruby (which I do not know) to vanilla JavaScript. It was a comedy of failing nonsense as I tried to get gpt-4.1 to help, and it just led me down pointless rabbit holes. I installed Gemini CLI out of curiosity, pointed it at the Ruby project, and it did the conversion from a single request, total time from "think…

<3 love to hear it!

Re: Gemini CLI

#154

Post by masklinn »

qsort wrote: post #43
ZeroCool2u wrote: post #22

Ugh, I really wish this had been written in Go or Rust. Just something that produces a single binary executable and doesn't require you to install a runtime like Node.

Projects like this have to update frequently, having a mechanism like npm or pip or whatever to automatically handle that is probably easier. It's not like the program is doing heavy lifting anyway, unless you're committing outright programming felonies there shouldn't be any issues on modern hardware. It's the only argument I can think of, something like Go would be goated for this use case in principle.

> having a mechanism like npm or pip or whatever to automatically handle that is probably easier

Re-running `cargo install ` will do that. Or install `cargo-update`, then you can bulk update everything.

And it works hella better than using pip in a global python install (you really want pipx/uvx if you're installing python utilities globally).

IIRC you can install Go stuff with `go install`, dunno if you can update via that tho.

Re: Gemini CLI

#156

Post by asadm »

Mond_ wrote: post #105

Oh hey, afaik all of this LLM traffic goes through my service! Set up not too long ago, and afaik pretty load-bearing for this. Feels great, just don’t ask me any product-level questions. I’m not part of the Gemini CLI team, so I’ll try to keep my mouth shut. Not going to lie, I’m pretty anxious this will fall over as traffic keeps climbing up and up.

do you mean the genai endpoints?

Re: Gemini CLI

#157

Post by cperry »

thimabi wrote: post #137
cperry wrote: post #96

Earlier quoted context omitted.

[edit] all lies - I got my wires crossed, free tier for Workspace isn't yet supported. sorry. you need to set the project and pay. this is WIP. Workspace users [edit: cperry was wrong] can get the free tier as well, just choose "More" and "Google for Work" in the login flow. It has been a struggle to get a simple flow that works for all users, happy to hear suggestions!

Thanks for your clarification. I've been able to set up Gemini CLI with my Workspace account. Just a heads-up: your docs about authentication on Github say to place a GOOGLE_CLOUD_PROJECT_ID as an environment variable. However, what the Gemini CLI is actually looking for, from what I can tell, is a GOOGLE_CLOUD_PROJECT environment variable with the name of a project (rather than its ID). You might want to fix that di…

sorry, I was wrong about free tier - I've edited above. this is WIP.

noted on documentation, there's a PR in flight on this. also found some confusion around gmail users who are part of the developer program hitting issues.

Re: Gemini CLI

#158

Post by AJ007 »

wohoef wrote: post #135

A few days ago I tested Claude Code by completely vibe coding a simple stock tracker web app in streamlit python. It worked incredibly well, until it didn't. Seems like there is a critical project size where it just can't fix bugs anymore. Just tried this with Gemini CLI and the critical project size it works well for seems to be quite a bit bigger. Where claude code started to get lost, I simply told Gemini CLI to "…

Current best practice for Claude Code is to have heavy lifting done by Gemini Pro 2.5 or o3/o3pro. There are ways to do this pretty seamlessly now because of MCP support (see Repo Prompt as an example.) Sometimes you can also just use Claude but it requires iterations of planning, integration while logging everything, then repeat.

I haven't looked at this Gemini CLI thing yet, but if its open source it seems like any model can be plugged in here?

I can see a pathway where LLMs are commodities. Every big tech company right now both wants their LLM to be the winner and the others to die, but they also really, really would prefer a commodity world to one where a competitor is the winner.

If the future use looks more like CLI agents, I'm not sure how some fancy UI wrapper is going to result in a winner take all. OpenAI is winning right now with user count by pure brand name with ChatGPT, but ChatGPT clearly is an inferior UI for real work.

Re: Gemini CLI

#159

Post by SparkyMcUnicorn »

re5i5tor wrote: post #106
trostaft wrote: post #95

Earlier quoted context omitted.

AFAIK, Claude code operates on your subscription, no? That's what this support page says https://support.anthropic.com/en/articles/11145838-using-cla... Could have changed recently. I'm not a user so I can't verify.

In recent research (relying on Claude so bear that in mind), connecting CC via Anthropic Console account / API key ends up being less expensive.

If you're doing anything more than toying around, this is not the case.

Using the API would have cost me $1200 this month, if I didn't have a subscription.

I'm a somewhat extensive user, but most of my coworkers are using $150-$400/month with the API.

Post reply on HN