Skip to content

Update README.md #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
shreyashx16 merged 1 commit into from
Nov 23, 2025
Merged

Update README.md #12

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 14 additions & 14 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,21 +4,21 @@
> **An intelligent, agentic AI system that analyzes, explains, and auto-fixes code vulnerabilities — powered by NVIDIA NIM and AWS SageMaker.**


## 🚀 Overview
## Overview

**CodeGuardian** is an **AI-powered DevSecOps agent** that automatically scans source code, detects security risks, explains vulnerabilities in natural language, and suggests secure fixes.

It combines **static analysis** (like a linter) with **LLM-based reasoning** (like an expert security reviewer) — running as an **agentic system** powered by:

- 🧠 **NVIDIA NIM Inference Microservices**
- **NVIDIA NIM Inference Microservices**
- `llama-3-1-nemotron-nano-8B-v1` → reasoning and fix generation
- `retrieval-embedding-nim` → knowledge retrieval
- ☁️ **AWS SageMaker Endpoints** for scalable inference
- ⚙️ **FastAPI backend** and lightweight Python agent framework



## 🎯 Goal
## Goal

To make **secure software development autonomous**, by allowing developers to:

Expand All @@ -29,7 +29,7 @@ To make **secure software development autonomous**, by allowing developers to:



## 🧩 Key Features
## Key Features

| Feature | Description |
|----------|-------------|
Expand All @@ -42,7 +42,7 @@ To make **secure software development autonomous**, by allowing developers to:



## 🧠 Architecture
## Architecture

```

Expand Down Expand Up @@ -76,7 +76,7 @@ To make **secure software development autonomous**, by allowing developers to:



## 🧱 Folder Structure
## Folder Structure

```

Expand Down Expand Up @@ -116,7 +116,7 @@ CodeGuardian/
````


## ⚙️ Setup Instructions
## Setup Instructions

### 1️⃣ Clone the Repository
```bash
Expand Down Expand Up @@ -150,7 +150,7 @@ EMBED_ENDPOINT_NAME=retrieval-embed-endpoint
```


## ☁️ AWS & NIM Integration Setup
## AWS & NIM Integration Setup

### Step 1 — Deploy NIM Models on SageMaker

Expand Down Expand Up @@ -187,7 +187,7 @@ You’ll get JSON output containing:
* Risk summary


## 🧠 Example Output
## Example Output

```json
{
Expand All @@ -212,7 +212,7 @@ You’ll get JSON output containing:
```


## 🧩 Example API Endpoints
## Example API Endpoints

| Endpoint | Method | Description |
| ---------- | ------ | ---------------------------------------- |
Expand All @@ -221,7 +221,7 @@ You’ll get JSON output containing:
| `/chat` | POST | Ask questions about issues interactively |


## 🧪 Running Tests
## Running Tests

```bash
pytest -v
Expand All @@ -234,7 +234,7 @@ CI also runs automatically via GitHub Actions:
* Optional embedding index build


## 🐳 Docker Setup
## Docker Setup

Build and run locally:

Expand All @@ -246,7 +246,7 @@ docker run -p 8080:8080 codeguardian
Access: `http://localhost:8080/docs`


## 🧠 Knowledge Base (KB)
## Knowledge Base (KB)

Includes 50+ security patterns and best practices:

Expand All @@ -258,7 +258,7 @@ Includes 50+ security patterns and best practices:
Stored in `agent/knowledge_base.py` and indexed via Embedding NIM.


## 🧩 Technologies Used
## Technologies Used

| Area | Stack |
| ---------------- | ------------------------------------ |
Expand Down