B
Story
Now open for building: Introducing Gemini CLI extensions
MCP servers already have the features they’re touting (preloaded prompts, custom commands etc.) so these features are redundant for most people.

But nice of them to try wrestling a file into your repo named “gemini something something”.. can’t knock them for having a go.

It looks like the key idea here is that a GitHub repo can have a gemini-extension.json file which specifies some MCP servers and a GEMINI.md file, then you can tell Gemini CLI to add that repo and it will fetch and configure those details.

Here's a commit I found adding one of these for the Google Maps platform: https://github.com/googlemaps/platform-ai/commit/95c4efdb43c...

Any Claude Code users who have tried Gemini CLI? Just curious as to how it compares.

I feel no desire to switch or learn a new thing but I'm wondering if people feel like it's on par with CC or Codex or behind.

My experience was while it had longer context it didn’t do as well on coding tasks. I use CC after being on Cursor.
Same with me, I had signed up for a year plan on Cursor, used it for like... a week, then tried CC and it was so much better I signed up for the max plan and then never looked back.
"The extensions listed here are sourced from public repositories and created by third-party developers. Google does not vet, endorse, or guarantee the functionality or security of these extensions. Please carefully inspect any extension and its source code before installing to understand the permissions it requires and the actions it may perform. "

Extensions are always a trust challenge, but the high value of AI systems means that I expect we'll see a very high volume of attacks in the near future.

Is it not strange that they didn't start with a Google Workspace extension? Drive, Docs, Sheets, Chat?
I think those have been around for ages already? At least via the app.
Well, this is about the CLI. I do mean the CLI.
My recent experience of Gemini CLI in comparison to Claude code is very negative. For a complex task of trying to migrate some code base from CPU-only to GPU computations Claude was really helpful, and allowed me to conduct a range of experiments and converge towards sensible architecture. In the same time I simply was not able to get anything useful out of Gemini. Some code was written, but it was not tested, was failing or timing out and after repeated prodding Gemini got into loops or internal errors.
  • chewz
  • ·
  • 1 hour ago
  • ·
  • [ - ]
Watching Gemini CLI repo daily is great insight into how Google works. Tons of commits, three release channels, great ambitions and very little to show. These guys are running in all directions and getting nowhere.
Cool, but at the same time, it feels overwhelming: so many different CLI or IDE tools, so many extension points. It will be fascinating to see how this all shakes out.
not in gemini-cli's flavor, it's one of the worst tools I've used
Is it model quality or the CLI itself?
  • asdev
  • ·
  • 4 hours ago
  • ·
  • [ - ]
so just a way to be able to pull in more context/info about MCP servers in the form of .MD files?
  • rs186
  • ·
  • 2 hours ago
  • ·
  • [ - ]
Someone please explain to me the value of being able to interact with Figma via Gemini CLI?

Why would I want to do that?

Presumably the reverse would be more valuable: design something in Figma, then have Gemini CLI read from Figma and use that as a reference while writing the code.

I don't know if this is how the Figma integration works, but right now I'm just manually screenshotting my designs and passing them into Claude CLI as references for what I want, so this seems potentially more streamlined.

The last time I was locked out of Claude Code I gave gemini cli a try. 10 minutes and lots of weird scrolling and screen flashing later, and it kept trying to add and remove the same function from the same file over and over, in a loop, until it exhausted its credits and demanded I upgrade.