Hello, I'm Maneshwar.
I'm building git-lrc, a Micro AI code reviewer that runs on every commit.
It is free and source-available on Github.
Star git-lrc to help devs discover the project.
Do give it a try and share your feedback.
A few years ago the AI conversation looked like this. "Should I pay $20?" "No, $200." "Actually this new tool is $39/month." My wallet started looking like it had gone through a startup funding winter.
Then Google quietly walked into the room and started dropping free AI tools like Oprah handing out cars. "You get an AI IDE!" "You get a workflow builder!" "You get a GitHub coding agent!" ...except nobody really noticed because Google announced them across five different events, Labs pages, GitHub repos, and random blog posts.
So I spent some time collecting the ones developers will actually find useful.
No "AI that writes your wedding speech." No "AI that guesses your spirit animal." Just tools that can actually help you ship software.
Bookmark this one.
1.
Pomelli https://labs.google/pomelli If you've ever launched a side project, you already know the painful truth.
Building the product is fun.
Writing 37 LinkedIn posts explaining the product... not so much.
Pomelli takes your website, understands what your product does, builds a brand profile, then generates social posts around it.
Think of it as hiring an intern that actually reads your landing page before tweeting.
Would I let it post automatically?
No.
Would I happily let it generate the first draft so I don't stare at a blinking cursor?
Absolutely.
Perfect for: Indie hackers SaaS founders Open-source maintainers pretending they enjoy marketing
2.
Stitch https://stitch.withgoogle.com Remember when designing an app meant opening Figma... ...moving a button 3 pixels... ...asking for feedback... ...moving it back 3 pixels?
Stitch skips a surprising amount of that.
You describe the interface.
Or upload a sketch.
Or even paste a wireframe.
It generates modern UI designs and can even produce frontend code.
It's not replacing designers.
It's replacing the blank canvas.
That's a huge difference.
3.
Antigravity https://antigravity.google/ Every AI company apparently wakes up and decides: "You know what?
Let's build another code editor." Google joined the party with Antigravity.
Prompt it.
Generate an app.
Modify code.
Refactor.
Debug.
Sound familiar?
Yes.
But competition here is fantastic.
Cursor, Claude Code, Windsurf and now Google all trying to out-build each other means developers keep winning.
I'm perfectly okay being the spoiled child in this particular custody battle.
4.
Mixboard https://labs.google/mixboard Imagine Canva and Pinterest had an AI-powered child.
That's Mixboard.
Instead of generating one image... ...you generate multiple concepts.
Mix.
Match.
Replace.
Rearrange.
Build moodboards.
For landing pages, presentations, branding, thumbnails, or app inspiration, it's surprisingly useful.
5.
Disco https://labs.google/disco This one's still on the waitlist.
The idea is interesting though.
Instead of opening 15 tabs and manually connecting information, Disco understands what's already in your browser and lets AI interact with everything together.
Think NotebookLM... ...except your browser becomes the notebook.
I'm curious to see where this one goes.
6.
NotebookLM https://notebooklm.google This one deserves way more attention.
Feed it: PDFs Docs YouTube videos Notes Research papers Then ask questions.
Generate summaries.
Create study guides.
Even generate podcast-style conversations.
I've thrown technical RFCs into NotebookLM before.
Reading 80 pages?
No thanks.
Asking "Explain this architecture like I'm joining the team tomorrow"?
Now we're talking.
7.
Learn Your Way https://learnyourway.withgoogle.com/ This feels like Google quietly built a personalized teacher.
Pick a topic.
It creates a learning path around you, not around a generic syllabus.
Want to learn Kubernetes?
It builds the course.
Rust?
Same.
Machine Learning?
Done.
It's surprisingly refreshing compared to watching fifteen random YouTube videos hoping they eventually connect.
8.
Flow Music https://www.flowmusic.app/ Not exactly a developer tool.
Still cool.
You describe the music.
AI produces songs.
Even music videos.
If you've ever wanted your side project launch trailer to sound slightly more cinematic than royalty-free ukulele music... here you go.
9.
Google AI Studio https://aistudio.google.com/ This is probably the tool developers should spend the most time with.
Prototype prompts.
Test Gemini models.
Build AI apps.
Experiment with structured outputs.
Play with APIs.
Break things.
Fix them.
Repeat.
Think of it as Google's playground where ideas become prototypes ridiculously fast.
10.
Jules https://jules.google/ This one feels like hiring an eager junior developer.
Connect GitHub.
Assign work.
It creates branches.
Implements changes.
Opens pull requests.
It won't replace senior engineers.
But handing it repetitive tasks?
That's where it gets interesting.
Especially for bug fixes, migrations and mechanical refactors.
11.
Gemini CLI https://github.com/google-gemini/gemini-cli If your happy place looks like this... ...Gemini CLI belongs on your machine.
Run commands.
Generate code.
Explain repositories.
Execute workflows.
All without leaving the terminal.
Because apparently opening browsers is becoming optional now.
12.
Codewiki https://codewiki.google/ Open a repository.
Instead of manually reading fifty folders... ...you get a wiki explaining the architecture.
How components connect.
What each module does.
Why things exist.
If you've ever cloned an unfamiliar repository and immediately typed: This is your answer. (If you've used DeepWiki before, you'll immediately understand the appeal.) Final Thoughts The interesting part isn't that Google released twelve AI tools.
It's that they're covering almost every stage of building software.
Need ideas?
NotebookLM.
Need UI?
Stitch.
Need code?
Antigravity or GeminiCLI.
Need automation?
Opal.
Need marketing?
Pomelli.
For a company that used to be "the search engine," Google suddenly looks a lot more like an end-to-end developer platform.
The AI race isn't just about building smarter models anymore.
It's becoming a battle over who owns your entire workflow.
And as developers... ...we get to steal the best parts from everyone.
So yes, bookmark this list.
Six months from now you'll probably remember that "Google had that one free tool..." Now you'll know exactly which one.
AI agents write code fast.
They also silently remove logic, change behavior, and introduce bugs — without telling you.
You often find out in production. git-lrc fixes this.
It hooks into git commit and reviews every diff before it lands. 60-second setup.
Completely free.
Any feedback or contributors are welcome!
It's online, source-available, and ready for anyone to use. ⭐ Star it on GitHub: HexmosTech / git-lrc Free, Micro AI Code Reviews That Run on Git Commit | 🇩🇰 Dansk | 🇪🇸 Español | 🇮🇷 Farsi | 🇫🇮 Suomi | 🇯🇵 日本語 | 🇳🇴 Norsk | 🇵🇹 Português | 🇷🇺 Русский | 🇦🇱 Shqip | 🇨🇳 中文 | 🇮🇳 हिन्दी | git-lrc Free, Micro AI Code Reviews That Run on Commit GenAI today is a race car without brakes.
It accelerates fast -- you describe something, and large blocks of code appear instantly.
But AI agents silently break things: they remove logic, relax constraints, introduce expensive cloud calls, leak credentials, and change behavior -- without telling you.
You often find out in production. is your braking system.
It hooks into and runs an AI review on every diff before it lands. 60-second setup.
Completely free.
In short, git-lrc helps Prevent Outages, Breaches, and Technical Debt Before They Happen At a glance: 10 risk categories · 100+ failure patterns tracked · every commit… View on GitHub