Google AntiGravity - Anyone using it ?

[2097]

What a wonderful tool it is !

 

I have been trying to implement some web-tools for a while , but no luck in finding in what i really needed.

 

Until someone on here mentioned using Antigravity for creating a Laptop booking software .

 

Here is some of the Tools i have created so far with it , I host them internal only on Apache/Mysql . Normally secured against a Azure app also SSO .

 

 

Laptop Booking System - Single / Mass booking - Sims timetable import . Admin Panel logs everything and allows removal etc 

 

 

Photo Booth - Allows self service taking of Photo/Sims iD images using a webcam , AI model removes the background and saves into the correct dimensions for Sims and the ID card software , saves them to a central database and names the files . Gives the user also the ability to download their photo , retake and Countdown etc .

 

 

AI Check - Its a web based AI checker for staff , supports copied and pasted text and Multiple file uploads , When uploading it will allow the input of a pupil name next to a document so you can assign it . Produces a report for each upload , highlights the text etc . The tool downloads the model into the staffs temporary files on their machine, so its basically a offline AI check Tool.

 

 

 

 

Edited July 30 by 2097

[dhicks]

2 hours ago, 2097 said:

Here is some of the Tools i have created so far with it , I host them internal only on Apache/Mysql . Normally secured against a Azure app also SSO .

 

Ah - just having a look at this today, I have a couple of existing projects I'd like to point an AI tool at and see what issues / improvements it can find. I'm aiming to have an "app" that is a self-contained compiled Go executable, complete with functionality, a web-based front-end and API documentation embedded in that executable. Should be self-hostable on any OS / architecture, with the option to be run on a server and handle user authentication via an authenticating reverse proxy (Pangolin, Cloudflare). So far, I've got as far as getting the client installed and authenticated inside my development environment, I'll see how I get on from there.

[2097]

14 minutes ago, dhicks said:

 

Ah - just having a look at this today, I have a couple of existing projects I'd like to point an AI tool at and see what issues / improvements it can find. I'm aiming to have an "app" that is a self-contained compiled Go executable, complete with functionality, a web-based front-end and API documentation embedded in that executable. Should be self-hostable on any OS / architecture, with the option to be run on a server and handle user authentication via an authenticating reverse proxy (Pangolin, Cloudflare). So far, I've got as far as getting the client installed and authenticated inside my development environment, I'll see how I get on from there.

 

Sounds very Interesting .

 

I am currently working on a Paxton net2 Bulk policy updater and easy event log exporter into PDF .

 

All Our sixthform kids are imported into Paxton from Entry sign with no policy , and then i get given a list of who i need to manually adjust to allow out of the gate etc .

 

In a few hours i have a working design for Bulk changing 

 

 

[dmj]

1 hour ago, dhicks said:

 

Ah - just having a look at this today, I have a couple of existing projects I'd like to point an AI tool at and see what issues / improvements it can find. I'm aiming to have an "app" that is a self-contained compiled Go executable, complete with functionality, a web-based front-end and API documentation embedded in that executable. Should be self-hostable on any OS / architecture, with the option to be run on a server and handle user authentication via an authenticating reverse proxy (Pangolin, Cloudflare). So far, I've got as far as getting the client installed and authenticated inside my development environment, I'll see how I get on from there.

As you are a 'Google School' IIRC. I would suggest looking at CloudRun fronted by Identity Aware Proxy - that how we are doing that. 

 

WRT the vibe coding aspect. I'm currently flitting between Zed (editor) using GPT-5.6-sol and Claude Code (opus 5). Occasionally I use OpenCode with either of those models. 

Not looked at antigravity for a while, when I did I (personally) found the Gemini models the worst out of GPT/Sonnet/Opus. I'm quite keen to get my hands on Kimi3 and GLM-5.2 my company is so far restricting us to the U.S. models, which is weird because they are more restrictive and more expensive. 

Edited July 30 by dmj

[dhicks]

1 hour ago, dmj said:

As you are a 'Google School' IIRC. I would suggest looking at CloudRun fronted by Identity Aware Proxy - that how we are doing that.

 

I've set up my own development and hosting environment hosted on a basic OVH VM and am using Pangolin to handle user authentication and proxy-ing. My aim is to have an environment self-hostable by a school so that all data can be kept within the organisation, but with the ability to use cloud-based filesystems and AI engines as wanted. I want to try out Antigravity to see how it works and how our staff and pupils might work with it. At the moment it's asking me for permissions for each command it wants to run, which I think user would find a bit tedious / confusing, so I'm maybe thinking some kind of default config file for a user's development area.

[dmj]

3 minutes ago, dhicks said:

 

 At the moment it's asking me for permissions for each command it wants to run, which I think user would find a bit tedious / confusing, so I'm maybe thinking some kind of default config file for a user's development area.

AFAIK there's not an equivalent to https://code.claude.com/docs/en/auto-mode-config in antigravity, last time I looked it was 'dangerously skip permissions' or click each time. 

Opencode is a lot more flexible FWIW.

[dhicks]

8 minutes ago, dmj said:

AFAIK there's not an equivalent to https://code.claude.com/docs/en/auto-mode-config in antigravity, last time I looked it was 'dangerously skip permissions' or click each time.

You seem to be able to give it a persistent list of commands it can run (mkdir, rm, git, go, etc), and define folders in which it is supposed to work. I'm not sure how well that holds - don't know if it can do a "rm ../../x.y.z" if it has general "rm" permissions.

 

Hmm - I've also just ran out of credit on my free introductory account, credits refresh in a week. This is after a couple of hours and maybe half a dozen prompts - admittedly asking it to create an entire Git repository, but this does look like a way to go through credit at a fair clip. This is with my own account, not school's - I'm not sure how credit for Antigravity gets applied to our school accounts.

[dhicks]

1 hour ago, dmj said:

Opencode is a lot more flexible FWIW.

Ah, yes, I see what you mean - it looks like I can pick-and-choose models and they have a pay-as-you-go option for what looks like a good selection of the main models, rather than having to sign up for a subscription.

[dmj]

4 hours ago, dhicks said:

This is with my own account, not school's - I'm not sure how credit for Antigravity gets applied to our school accounts.

A good method is billing via GCP enterprise agent platform (formerly vertex). You can setup a GCP project and enable the necessary API's, then Claude Code/Opencode can bill directly through the GCP project. (not sure about Antigravity, but given it is Google I would be surprised if it didn't) There are some models as a service and pay per token (as opposed to hosting your own model). All the Gemini and Anthropic models allow this along with some of the openweight models.  Openrouter is also a popular choice.

[dhicks]

15 hours ago, dmj said:

A good method is billing via GCP enterprise agent platform (formerly vertex).

 

I'm looking at how to handle AI tools and billing for our staff and pupils. We already pay for Google's Gemini, which gives our users access to the web-based chat interface and embedded into GMail and so on, but doesn't seem to include the API to use with coding tools - as you point out, we have to go and set up separate billing in a GCP Project. I can see the costs there starting to get out of hand quite easily if we simply let staff and pupils set coding harnesses and AI assistants running.

 

Is anyone hosting a local AI engine? Looking at the available options, a Mac Mini with 48GB of RAM is around £2,500, which as a central server handling AI processing for a number of users might be a cheaper option that paying for API usage.

 

I'm now trying out OpenCode on my test development environment. It turns out to be more resource-heavy than the Gemini CLI client, needing a bit of poking before it would work inside the 2GB-of-RAM container I've assigned it. It's currently using the (currently free!) Big Pickle engine, which has managed to create a whole Git repository containing a Go application and then got itself in a loop trying to add a simple relative web page link. I might try the Pi coding agent, as seemingly that is less resource-heavy.

[dhicks]

1 hour ago, dhicks said:

which has managed to create a whole Git repository containing a Go application and then got itself in a loop trying to add a simple relative web page link.

Gah! This actually turned out to be a bug in the web server (a small custom Go web server from a separate project of mine). Suitably impressed.

[dmj]

1 hour ago, dhicks said:

 

Is anyone hosting a local AI engine? Looking at the available options, a Mac Mini with 48GB of RAM is around £2,500, which as a central server handling AI processing for a number of users might be a cheaper option that paying for API usage.

 

I'd love to do that, but I'm pretty sure to get anywhere close to gemini/Claude/GPT you'll need a £250k rig. Closest next best thing is GCP hosted but at $148 per hour ...

[dmj]

With regards to creating git repos, cookie cutter might be a good option for students to clone, with the basics in there

https://github.com/cookiecutter/cookiecutter 

You can drive the cli from your agent and it will use fewer tokens 

[mavhc]

I've used various LLMs to make my Archive Printer system, identify filetypes, parse excel files, search for files, merge with other folders, and combine log files into spreadsheets, all with the free models. In agy.exe /quota shows you your remaining quota, when it runs out /model to switch then I just say "continue". Basically any small task is now automated

[dhicks]

On 31/07/2026 at 18:45, mavhc said:

In agy.exe /quota shows you your remaining quota, when it runs out /model to switch then I just say "continue".

 

For the moment, I'm using OpenCode with their "Zen" pay-as-you-go LLM service - still currently on the default free Big Pickle model, I've not had to spend any money there yet. I've started with making a basic image-processing app, for which I've also wound up paying for OpenRouter so I can use their (also pay-as-you-go) API to pass images to for processing. This is all currently on my own infrastructure and accounts (and I am quite impressed you can fit all this into a basic 2GB RAM and 40GB disk VM). Issues that would need addressing for this sort of thing to be usable by staff / pupils:

 

- Some kind of per-user token budget, pretty much exactly like we currently give staff a printer budget.

- Some kind of keyword / image filtering for submitted prompts and resources, filtered in the same way we would for search queries and so on.

- Clarity on what happens to data sent to an AI service - a school (like any corporate) would need a data-stays-private, doesn't-get-used-for-training guarantee.

 

To me, the above rather implies some kind of local AI API proxy server - something that allows administrators to tightly control budgets and handle filtering. Possibly using Zen / OpenRouter as a backend, but with a further curated set of models that meet school's privacy requirements.

 

Does such an application / service already exist?

[jthompson]

There was me thinking I was clever rolling out lots of automation and custom applications using combinations of Apps Script, AppSheet and PowerShell.

 

Is this the sort of stuff I need to be getting to grips with in order to not have my job disappeared by somebody/something else?

[dhicks]

1 hour ago, jthompson said:

Is this the sort of stuff I need to be getting to grips with in order to not have my job disappeared by somebody/something else?

 

So, using an AI coding agents, I've managed to create in one day a (small, single-page) app I've been wanting to get around to for a while (user takes photo / uploads image, some processing is done, file gets written to cloud drive). I'm not sure how much of that speed of development is down to my existing knowledge / expertise - I've constrained the agent to only working in a way I can understand (a simple, single-file Go project, a single-page, quite basic web interface using Bootstrap). I am able to describe quite precisely what I want done, and if there's an issue I know how to figure out where the issue is. I've also created the environment the app runs in, which already takes care of some of the functionality (e.g. cloud filesystem mounted as a local file system). It would be interesting to see how, say, a year 10 or so pupil would approach the same problem and what additional tools / capabilities they might need. I'm currently using a couple of terminal windows and a separate browser to test the app, I suspect that might be a bit much for the average pupil (or member of staff) and something nicely all-in-one that runs in a browser would be best.

[2097]

Another one added to the Arsenal , AI redone the original logintracker that was posted on edugeek many years ago .

 

Made a few modifications , Still uses a VBS login and logoff script to monitor logins.

 

Redone the GUI

 

Uses SSO from azure to access the frontend .

 

Reads Entra Logs for laptop logins.

 

Can determine either student or staff via the OU of the user.

 

also added a print PDF button , which makes a nice table in a printable format to print out the logins for admin purposes.

 

Also added a calendar option which allows me to choose a date and show all logins for that specific date.

 

[2097]

Oh Also forgot it created me another utility , Our Paxton Net2 system , Currently within sixth form we only allow specific people to use the gate system for lunchtime . With Net2 there was no way to Bulk assign a policy ( apart from SQL ) . So i created the following GUI to allow this.

 

[dhicks]

So, a couple of days and around £20 in AI tokens has produced this:

 

https://www.sansay.co.uk/magooify/demo/

 

A somewhat specialised application for a specific image editing workflow - useful (hopefully) for the person wanting to use it, but rather niche otherwise. That would seem to be a strength of AI coding tools - I can now make tools for a "market" of one / a few people, and it's affordable and do-able in a reasonable timeframe. Using Go as the implementation language seems to have worked well and has produced an application capable of running on most hardware and with minimal resources - the live version is running on a VM with 2GB of RAM and 80GB of disk space, and that's for the whole system including authenticating proxy server (Pangolin), code to mount cloud file systems and the OpenCode tool for development.

[dmj]

On 31/07/2026 at 12:09, dhicks said:

Is anyone hosting a local AI engine? Looking at the available options, a Mac Mini with 48GB of RAM is around £2,500, which as a central server handling AI processing for a number of users might be a cheaper option that paying for API usage.

 

@dhicks

Apparently The Alibaba qwen 3.8 27B model is very good for local work. 

I tried it on a 24GB M4 pro (ollama and opencode) and instantly ran out of memory, but it might work on a 48GB ?

Here's a good writeup (on a 128GB M5) https://simonwillison.net/2026/Aug/16/qwen-38-27b/

Edited August 17 by dmj

[dhicks]

8 hours ago, dmj said:

Apparently The Alibaba qwen 3.8 27B model is very good for local work.

 

Hmm - we have Summer 2024-era 8GB-of-RAM iMacs in our ICT suite, I wonder if it's worth trying to run a local model of some sort on those?

[dmj]

2 hours ago, dhicks said:

 

Hmm - we have Summer 2024-era 8GB-of-RAM iMacs in our ICT suite, I wonder if it's worth trying to run a local model of some sort on those?

Perhaps llama RPC and share the model across all the hosts it's experimental but worth a shot https://github.com/ggml-org/llama.cpp/blob/master/tools%2Frpc%2FREADME.md

[2097]

So a new day and a new project to get something going for me .

 

As much as salamander looks great , I only needed it for the Sim’s To MS Teams integration . ( not very cost effective )

 

So i decided to make my own 

 

Created a SIMs report to extract Classes and class lists and teachers into a simple CSV file ( automated using the commandreporter.exe , creates a new one each week with changes)

 

I have a PowerShell script that from the initial CSV file , will create every class , add every teacher as a owner and add every student as a member  . It will also create them a "Secure" folder in the General part of the team for them and the teacher to access ( I don’t think salamander does that ).

 

So basically i run two files each Year that will pre-populate my teams etc .

 

What about changes to Sims  ? Student Class moves , Class renames , Staff changing .

 

For the moment i dont want this automated as i want to see the changes and make sure the script is working correctly.

 

So I created a simple Web gui that takes the exports from commandreporter and compares them , this then prepares me a pre-made script which i can run and it will move , add , rename and move folders etc.

 

it also reports on all the differences and changes to make sure everything is correct within Sims.

 

 

 

 

 

[mavhc]

The days of SaaS are numbered when we can just create our own custom tools