brettinhere

brettinhere / Codong

Public

AI native programming language one correct way to write everything

19
0
100% credibility
Found Mar 26, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Go
AI Summary

Codong is a programming language designed specifically for AI to generate efficient, predictable code with built-in modules for web servers, databases, HTTP clients, and AI integrations.

How It Works

1
🔍 Discover Codong

You find Codong online, a simple way for AI to create working programs that you can easily check and run.

2
📥 Get it set up

Run one easy command to download and prepare Codong on your computer.

3
✏️ Write hello world

Type a short message like print('Hello, Codong!') into a file.

4
▶️ See it work

Run your file and watch 'Hello, Codong!' appear on screen.

5
🌐 Build a web app

Write a tiny program to serve web pages or data with one command.

6
🤖 Let AI code for you

Share the guide with any AI chat, ask it to build something, and run the code right away.

🎉 Your app is live

Enjoy your working web service or tool, made fast with AI help and easy review.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 19 to 19 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Codong?

Codong is an AI-native programming language built in Go that compiles to native Go binaries, designed so AIs can generate correct, efficient code without guesswork. It solves AI coding friction by enforcing one correct API per task—like a single `web.serve(port)` for servers or `db.connect(url)` for databases—plus structured JSON errors with built-in fixes. Developers get instant scripts via `codong eval`, dev servers with `codong run`, or production builds with `codong build`, all without package hunting.

Why is it gaining traction?

Its arena benchmark crushes Python/JS/Go on token use (955 vs 1,867+), code lines (10 vs 143+), and speed, proving real AI savings. No choices mean predictable output; paste the spec into any LLM and get runnable code. Built-in modules cover web APIs, DB CRUD, HTTP clients, and LLMs, slashing setup for 90% of agent tasks.

Who should use this?

AI workflow builders chaining LLMs for apps, like CRUD APIs or LLM-powered endpoints. Devs prototyping web services or reviewing agent code who hate framework roulette. Teams in codung nürnberg or github native alpha experiments wanting github native script for quick native meaning programming.

Verdict

Fun concept for AI code gen, but 19 stars and 1.0% credibility scream early alpha—skip for prod until tests stabilize and modules mature. Try the arena if you're into github native ui hacks like codong sushi nürnberg brunch demos.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.