Devlog 8

New

• Added OpenRouter free models API support
• The AI can use the Discord server’s custom emojis in its responses (emojis from the Discord cache)

Models (reminder)

All AI models are free and use free API keys (Groq, Gemini, HackClub, OpenRouter).

const geminiModels = ['gemini-2.5-flash', 'gemini-2.5-flash-lite']
const groqModels = ["openai/gpt-oss-120b", "openai/gpt-oss-20b", "qwen/qwen3.6-27b"]
const HackClubModels = ['meta-llama/llama-3.3-70b-instruct']
const visionModel = ["qwen/qwen3.6-27b", "qwen/qwen3.8-27b"]
const openroute = ["openrouter/free"]

Planned

I plan to continuously develop and improve this project.

Devlog 7

New

• Added CONTRIBUTING.md (how to add your language)
• New /help command with a description of all commands
• Finalized README.md with features, how to run it, etc.
• Added /logs command with live bot logs (question and AI model)

Planned

I plan to ship this project.

Devlog 6

New

• Added image support (vision, Qwen models)
• Added AI response error handling
• Added validation for Add custom AI reaction emoji (supports Discord emoji format)
• Added .env example in README.md
• Added MIT LICENSE on GitHub
• Added base AI prompt with a character limit (1500 characters)

Planned

I plan to add a /logs command.

Devlog 5

New

• New settings image
• Changed /ai_settings panel design
• Created 2 new bot emojis (success and failure)
• Added Discord emoji format support in the Add custom AI reaction emoji panel
• Added bot_name typing... indicator

Planned

I plan to add an embed AI response with an on/off option in /ai_settings.

Devlog 4

New

• Created the bot’s profile image
• Added the AI response system (with 15-message context history)
• Created the /ai_settings panel with custom prompt and thinking emoji options
• Extended the language files with new translation keys

Planned

I’m planning to add support for Discord’s custom emoji format in /ai_settings, and start working on a logs system showing the question asked and which AI model responded.

Devlog 3

New

• Added multi-language support
• Created /ai_settings panel
• Added English and Polish language support
• Added mention detection - the bot now checks if it was mentioned on the configured AI channel

Planned

I’m planning to connect the AI system to the bot’s replies and finish the custom prompt settings (via the modal opened from /ai_settings).

Devlog 2

New

• Created the Dockerfile and .dockerignore
• Set up a pre-built Docker image (built automatically via GitHub Actions)
• Created the /ai slash command
• Created save_data.js and a save system for the AI channel

Planned

I’m planning to create the bot’s profile picture and start working on getting AI responses inside Discord.

Devlog 1

New

• Added 3 AI providers: Groq, Gemini, HackClub
• Added 6 LLM models across those providers
• Tested the connection with each provider

LLM models

Gemini API

gemini-2.5-flash, gemini-2.5-flash-lite

Groq API

openai/gpt-oss-120b, openai/gpt-oss-20b, qwen/qwen3.6-27b

HackClub API

meta-llama/llama-3.3-70b-instruct

Planned

I’m planning to integrate these models with the Discord bot

Devlog 7

New

• Added a “Your flashcards folder” panel on the main page
• Fully functional flashcard study system (question/answer card with flip animation, folder selection, Next/Previous navigation)
• Pages now require login to access

Planned

I’m planning to ship my project.

Devlog 6

New

• Created a Docker image for the app (PHP + MariaDB in one container)
• Added a GitHub Actions workflow that builds the Docker image with buildx
• Added the ability to create and delete flashcards within a folder
• Added a live preview for the flashcard question and answer while typing
• Added a “Your flashcards” list showing existing flashcards in the folder

Planned

I’m planning to update the styling of the main page (index.php).

Devlog 5

New

• Added a “How to use” section
• Cleaned up the CSS (reorganized and simplified the code)
• Created the createflashcard.php file, with a query pulling the selected folder’s name

Challenges

Rebuilt the whole page layout using nested flexbox containers instead of the manual negative margins.

Planned

I’m planning to build the flashcard creation form for the selected folder.

Devlog 4

New

• Finished the “Your Folders” GUI
• Created the “Delete Folder” panel
• New styling for the create and delete buttons

Challenges

Spent a while debugging why my delete panel wouldn’t stay hidden

Planned

I’m starting work on the flashcard creation panel with a live preview of the flashcard.

Devlog 3

New

• Added a flashcard folder system (users can create folders to organize flashcards by subject)
• Started working on the “Your Folders” GUI
• Added a new user_id column to the subjects table, linked with a foreign key to users

Planned

I’m planning to finish the folder system.

Devlog 2

New

• New users table in the database
• Login and registration system with password hashing
• Login and registration website panels
• Login session system
• Logout system
• Mobile device support for login and registration panels
• Login and registration error handling

Login/Registration System

I built my first login and registration system, based on PHP and a MySQL/MariaDB database. I used the password_hash function for user security. I also added $_SESSION support across the website, so the app remembers which user is logged in between pages. The registration system requires a minimum of 8 characters for the password.

Planned

I’m planning to style the header tag and build the flashcards panel. I also plan to add the ability to export flashcards.

Devlog 1

New

• Planned work on the project
• Created the MySQL database
• Connected to the MySQL database
• Created a temporary flashcard design
• Added flashcard flip animation
• Created the schema.sql file

Idea

I am planning to create a flashcard web app with support for mobile devices and desktop. I will use the MySQL/MariaDB database for the application. For the backend, I will use the PHP language.

Devlog 12

New

• Built and published a Docker container on GitHub
• Added a progress bar for YouTube Downloader
• Disabled the OK button until the file is ready
• Adjusted YouTube Downloader GUI for mobile devices
• Added a 2GB file upload limit to FFvert
• Updated README.md

Docker

You can run the image using a pre-built Docker image.

docker pull ghcr.io/nahida4479/ffvert:latest
docker run -p 3003:3003 ghcr.io/nahida4479/ffvert:latest

or build it yourself

git clone https://github.com/Nahida4479/FFvert.git
cd FFvert
docker build -t ffvert .
docker run -p 3003:3003 ffvert

Devlog 11

New

• Section How to use
• Change name yt-dlp –> YouTube Downloader
• Full YouTube video download system

YouTube download video system:

I use the node package youtube-dl-exec for this system. The file is downloaded by the backend and converted using FFmpeg for the user-selected format. For GIF files FFmpeg generates a special palette for better color accuracy.