BroCheck — The Open-Source AI Roaster for Playlists, Code & GitHub Profiles

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

#

What I Built

We’ve all got that one friend whose taste and habits desperately need a reality check:

• The friend who puts Nickelback ,Baby Shark , andCrazy Frog on the same 3 AM roadtrip playlist.
• The developer friend who names variables temp_var_2_final_really_final and writes 600-lineif/else ladders.
• The friend whose GitHub profile has 0 green commit squares this year but their bio screams "10x Senior Full-Stack Architect" .
• The friend whose excuses for being 2 hours late to a group hangout defy the laws of physics.

To lovingly solve this problem, I built BroCheck — a lightweight, multi-mode terminal CLI powered by Open-Source AI that delivers customized, hilarious roasts on whatever you throw at it.

Key Features:

Universal Music Playlist Roaster : Drop any playlist link (Spotify, Apple Music, YouTube Music, SoundCloud ), local.txt /.m3u files, or raw artist lists. #

Code Review Roaster : Analyses any code file (.py ,.js ,.ts ,.cpp , etc.) for architectural and stylistic sins. #

GitHub Profile Roaster : Scrapes public GitHub stats, repos, and bios without requiring API keys, roasting developer habits. #

Social Bio & Status Roaster : Dismantles fake-deep gym quotes and corporate LinkedIn buzzwords. #

Chat Excuse Roaster : Calls out group chat lies and late arrival excuses. #

3 Heat Levels :Mild (playful banter),Spicy (sharp satire), andNuclear (pure comedic devastation). #

4 Personas :Best Friend (casual slang),Gordon Ramsay ("IT'S RAW!" ),Tech Bro VC (negative alpha / zero ROI), andDisappointed Parent ("Sharma-ji's son would never" ).

#

Demo

Here is BroCheck in action across different modes and personas:

1. Roasting a Friend's Roadtrip Playlist (Best Friend Persona, Spicy Heat)

2. Roasting Spaghetti Code (Gordon Ramsay Persona, Nuclear Heat)

#

Code

The entire codebase is open-source under the MIT license:

  BroCheck — a lightweight, multi-mode terminal CLI powered by Open-Source AI that delivers customized, hilarious roasts on whatever you throw at it.

The Open-Source AI Roaster CLI

Built for the Hacktoberfest 2026 (HF26) DEV Challenge: Build for a Friend

BroCheck is a zero-RAM, multi-mode AI roaster CLI that hilariously critiques your friend's music playlists, spaghetti code, barren GitHub profiles, cringey bios, and transparent excuses using Open-Source AI.

Features #

Universal Music Roaster : Drop any playlist link (Spotify, Apple Music, YouTube Music, SoundCloud ), upload a.txt /.m3u file, or paste raw song lists. #

Code Review Roaster : Point to any.py ,.js ,.ts ,.cpp file for a brutally honest critique of variable names and 6-level nested loops. #

GitHub Profile Roaster : Enter any GitHub username to roast empty commit heatmaps, abandoned test repos, and buzzword-packed bios. #

Social Bio & Status Roaster : Savage fake-deep gym quotes and LinkedIn buzzwords. #

Excuse & Chat Roaster : Roast terrible excuses for being late to group hangs. #

Adjustable Heat …

Project Structure:

#

How I Built It

BroCheck was built using Python and centered around open-source AI:

flowchart TD
    CLI[User Terminal / Interactive Wizard] --> Parser{Universal Input Parser}
    Parser -->|Spotify / Apple / YT Link| LinkExtractor[oEmbed & Metadata Scraper]
    Parser -->|.txt / .m3u File| FileHandler[Local File Reader]
    Parser -->|GitHub Handle| GHAPI[GitHub Public API]

    LinkExtractor & FileHandler & GHAPI --> PromptEngine[Prompt & Persona Builder]
    PromptEngine --> OpenEngine[Open-Weight AI Engine\nLlama-3.2 / Qwen-2.5 / Mistral]
    OpenEngine --> RichUI[Rich Terminal UI & Verdict Card]

Open-Weight Models : Powered bymeta-llama/Llama-3.2-3B-Instruct ,Qwen/Qwen2.5-Coder , andmistralai/Mistral-7B . 2. Universal Playlist Scraper : Leverages public oEmbed and metadata endpoints to parse links from Spotify, Apple Music, and YouTube without requiring private API tokens. 3. Public GitHub Fetcher : Retrieves repository names, commit frequencies, and bios directly from GitHub's public API. 4. Rich Terminal Engine : Provides an interactive setup wizard, spinners, result panels, and customizable terminal themes using Pythonrich .

#

Why Does Open Innovation Matter?

This project was developed on a machine with limited RAM (6GB), where running heavy local LLMs would cause system lag and memory thrashing.

Open innovation solved this completely:

Freedom of Open Weights : We utilize open-weight models (Llama-3.2 ,Qwen-2.5 ,Mistral ) instead of being locked into closed, proprietary platforms with unpredictable pricing and opaque modifications. 2. 0 MB RAM Footprint : By pairing a lightweight Python client harness with open serverless inference, anyone with budget or low-spec hardware can run and build AI tools with sub-second response times. 3. Friend Data Privacy : Personal group chat texts, private code snippets, and quirky playlist links are not fed into closed commercial model training loops. 4. Uncensored Creative Writing : Closed AI APIs often over-moderate playful humor and satirical character prompts. Open-weight models give developers full control over system instructions, enabling fun personas like Gordon Ramsay screaming at unseasoned code.

#

My Agent Session

This project was designed, planned, scaffolded, and tested with DevRelay and Antigravity.

Happy Hacktoberfest 2026! Protect your code, protect your aux cord.