Skip to main content

Advanced AI Developer OS

Project description

CodeAOIS

๐Ÿ’ป CodeAOIS (v0.3.0) - Advanced Developer OS

An elite, autonomous AI operating system for your terminal. CodeAOIS doesn't just chat; it reads your codebase, runs its own code, and fixes its own bugs.

๐Ÿ”ฅ Core Pillars

  1. Global Cloud Identity: Secure, OTP-based login via private SMTP. Your history, developer profile, and token usage follow you to any machine via Supabase.
  2. Autonomous Execution Loop: The OS executes generated Python scripts locally. If it hits a Traceback error, it autonomously feeds the crash data back to the LLM and self-corrects the code.
  3. Local Codebase Brain (RAG): Type /index to calculate embeddings for your entire local project. CodeAOIS instantly retrieves semantic context so you never have to copy-paste your code again.
  4. LLM Supervisor Engine: An intelligent routing system that determines if you want to chat, execute a terminal command, or write a new script, routing tasks to specialized agents seamlessly.

โšก Quick Start

pip install -r requirements.txt
codeaois

Advanced AI Developer Operating System

CodeAOIS is an experimental AI-powered developer operating system that allows developers to interact with an AI coding system directly from the terminal.

Instead of simple autocomplete tools, CodeAOIS acts like an AI developer partner capable of understanding instructions, generating code, and managing development workflows.

The system is designed around a multi-agent architecture where specialized agents collaborate to perform tasks such as coding, testing, and project management.


โœจ Features

โ€ข Natural language coding from terminal โ€ข Multi-agent AI architecture โ€ข Automatic code generation โ€ข Project context scanning โ€ข Agent marketplace system โ€ข AI memory and context tracking โ€ข Modular and extensible design


๐Ÿง  How CodeAOIS Works

CodeAOIS works like an AI operating system for developers.

You simply describe what you want to build, and the system:

  1. Understands your request
  2. Scans the project context
  3. Activates the appropriate AI agent
  4. Generates code
  5. Shows the preview before applying changes

Demo

CodeAOIS Terminal

CodeAOIS Terminal

AI Code Generation

Code Generation

Generated Login Page

Login Page


๐Ÿ’ป Example

Start CodeAOIS:

python app.py

Then type instructions like:

in file named index1.html you just make a colorful page and login page with css

CodeAOIS will:

โ€ข Analyze your intent โ€ข Activate the coder agent โ€ข Generate code โ€ข Display the preview

Example output:

[System] Analyzing intent...
[Code Mode] Engaging Coder agent...

Target file locked: index1.html
Scanning project context...
Generating code...

PROPOSED CODE GENERATION PREVIEW:
<!DOCTYPE html>
<html>
...

๐Ÿงพ Available Commands

/help            show command list
/marketplace     view specialized AI agents
/install <x>     install agent
/status          show system status
/clear           clear terminal
/clear_history   reset conversation memory
/clear_user      reset user profile
/exit            exit CodeAOIS

๐Ÿงฉ Project Structure

codeaois_project
โ”‚
โ”œโ”€โ”€ codeaois
โ”‚   โ”œโ”€โ”€ brain
โ”‚   โ”‚   โ”œโ”€โ”€ embeddings.py
โ”‚   โ”‚   โ”œโ”€โ”€ memory.py
โ”‚   โ”‚   โ””โ”€โ”€ scanner.py
โ”‚   โ”‚
โ”‚   โ”œโ”€โ”€ cli
โ”‚   โ”‚   โ””โ”€โ”€ main.py
โ”‚   โ”‚
โ”‚   โ”œโ”€โ”€ config
โ”‚   โ”‚   โ””โ”€โ”€ settings.py
โ”‚   โ”‚
โ”‚   โ”œโ”€โ”€ core
โ”‚   โ”‚   โ”œโ”€โ”€ context.py
โ”‚   โ”‚   โ”œโ”€โ”€ marketplace.py
โ”‚   โ”‚   โ”œโ”€โ”€ memory.py
โ”‚   โ”‚   โ”œโ”€โ”€ orchestrator.py
โ”‚   โ”‚   โ”œโ”€โ”€ planner.py
โ”‚   โ”‚   โ””โ”€โ”€ router.py
โ”‚   โ”‚
โ”‚   โ”œโ”€โ”€ models
โ”‚   โ”‚   โ””โ”€โ”€ llm_interface.py
โ”‚   โ”‚
โ”‚   โ””โ”€โ”€ utils
โ”‚       โ”œโ”€โ”€ file_writer.py
โ”‚       โ””โ”€โ”€ logger.py
โ”‚
โ”œโ”€โ”€ app.py
โ”œโ”€โ”€ requirements.txt
โ”œโ”€โ”€ setup.py
โ””โ”€โ”€ pyproject.toml

โš™๏ธ Installation

Clone repository:

git clone https://github.com/C0de-With-Nikhil/CODEAOIS_PROJECT.git

Go to project folder:

cd CODEAOIS_PROJECT

Create virtual environment:

python3 -m venv venv
source venv/bin/activate

Install dependencies:

pip install -r requirements.txt

Run CodeAOIS:

python app.py

๐ŸŽฏ Vision

The goal of CodeAOIS is to create a true AI development operating system capable of:

โ€ข autonomous coding โ€ข project reasoning โ€ข multi-agent collaboration โ€ข automated debugging โ€ข AI-driven software architecture


โš ๏ธ Status

CodeAOIS is currently an experimental research project and under active development.


Installation

pip install codeaois

Usage

codeaois

2. The Master Blueprint (setup.py)

Now we need the configuration file. You might already have a basic one from earlier, but we need the production-ready version.

Create or overwrite the setup.py file in your root ~/codeaois_project/ folder with this exact code:

# ๐Ÿ‘จโ€๐Ÿ’ป Author

Created by **Nikhil Nagar**

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

codeaois-0.3.0.tar.gz (29.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

codeaois-0.3.0-py3-none-any.whl (34.4 kB view details)

Uploaded Python 3

File details

Details for the file codeaois-0.3.0.tar.gz.

File metadata

  • Download URL: codeaois-0.3.0.tar.gz
  • Upload date:
  • Size: 29.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for codeaois-0.3.0.tar.gz
Algorithm Hash digest
SHA256 a70aa8749ace8898f1ca4277ca53f9393a216f7e18a3240f86bbad57357b13c1
MD5 920eb77a716e9f534ab179237e30e04c
BLAKE2b-256 3c4e9f32dfc42c11bd75ac708302f9c6e6294130b87d4bcf3b3dba7d68a676a5

See more details on using hashes here.

File details

Details for the file codeaois-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: codeaois-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 34.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for codeaois-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 31926047ddf3920288fa4f6e6459c3abce3902ab50ea7c38d2865a25bd885eac
MD5 1220dcae21451fe87293cd0b6a334f5c
BLAKE2b-256 8db8cbd2bbb7bb5435b9d0feaeffc347244fac769a916d33a7c5caaed1c9e79a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page