Team Ai
Apppublic

juliensimon/trinity-code-reviewer

sourceHugging Facemitupdated 7mo agoView on Hugging Face
5likes
App README

Arcee AI Trinity Large Code Review

AI-powered code review that streams real-time analysis of any public GitHub file using Arcee AI's Trinity Large model via OpenRouter.

<p align="center"> <img src="https://img.shields.io/badge/Model-Trinity%20Large-purple" alt="Trinity Large"> <img src="https://img.shields.io/badge/API-OpenRouter-blue" alt="OpenRouter"> <img src="https://img.shields.io/badge/Streaming-SSE-green" alt="Server-Sent Events"> <img src="https://img.shields.io/badge/License-MIT-yellow" alt="MIT License"> </p>

How It Works

  1. 1.Paste a public GitHub file URL (e.g., https://github.com/owner/repo/blob/main/file.py)
  2. 2.Choose a review tone: Gentle (supportive mentor), Standard (Linus Torvalds-style), or Brutal (volcanic rage)
  3. 3.Get a streaming code review across 6 categories

Review Categories

CategoryWhat It Covers
SummaryHigh-level overview of the file's purpose and structure
Code QualityIssues tagged as [CRITICAL], [HIGH], [MEDIUM], or [LOW] severity
PerformanceAlgorithmic inefficiencies, memory leaks, unnecessary allocations
SecurityInjection risks, authentication issues, data exposure
SuggestionsConcrete improvements with inline diff blocks
VerdictsOpinions from Linus Torvalds, Donald Knuth, and Bjarne Stroustrup

Tech Stack

  • —Backend: Node.js + Express with Server-Sent Events (SSE)
  • —Frontend: Vanilla HTML/JS with tabbed interface, syntax highlighting, and diff rendering
  • —Model: arcee-ai/trinity-large-preview:free via OpenRouter
  • —Deployment: Docker on Hugging Face Spaces

Run Locally

bash
git clone https://huggingface.co/spaces/juliensimon/trinity-code-reviewer
cd trinity-code-reviewer
echo "OPENROUTER_API_KEY=your_key_here" > .env
npm install
node server.js

Opens at http://localhost:3000.

License

MIT