Build a Chrome extension or frontend that chats with an AI model while remembering session context.
Summarize a YouTube video by extracting its captions and generating a short topic review.
Extract readable text from an uploaded PDF or scrape and clean the text of a public webpage.
Translate text between languages for free without needing a paid translation API key.
| randomassdude696969/ai.dly | 0xhassaan/nn-from-scratch | 3ks/embedoc | |
|---|---|---|---|
| Stars | 0 | 0 | — |
| Language | Python | Python | Python |
| Last pushed | — | — | 2023-06-08 |
| Maintenance | — | — | Dormant |
| Setup difficulty | moderate | moderate | hard |
| Complexity | 3/5 | 4/5 | 1/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires a Together AI API key plus system-level yt-dlp and curl installed for YouTube transcript features.
AI.dly is a backend server that bundles together several AI-powered features into one API, meant to be used by a companion Chrome extension. It was originally built by the author for a school research project and later used in a tech competition, at a time before they knew about GitHub. The server can hold a multi-turn chat conversation with memory of what was said earlier, summarize the transcript of a YouTube video by pulling its captions, read and extract text from an uploaded PDF file, scrape a webpage and return its cleaned readable text, and translate text between languages without needing any paid translation service. It can also write a short essay on a given topic using an AI model. All of the AI-generation features, like chat, essays, and summaries, are powered by Together AI, a service that provides access to large language models, which requires you to sign up for your own free API key. Under the hood it is a Flask application written in Python, using tools like PyMuPDF to read PDF files, Beautiful Soup to parse webpages, yt-dlp to fetch YouTube captions, and a translation library that works without an API key. Each feature is exposed as its own web address that a frontend, such as the companion Chrome extension, can send requests to and get a JSON response back. To run it yourself, you need Python 3.12 or newer, the yt-dlp and curl command line tools installed on your computer, and a Together AI account to get an API key, which you either paste directly into the code or set as an environment variable for better security. After installing the Python dependencies with pip, you start the server with a single command and it becomes available on your local machine. The README does not mention a license, so it is unclear under what terms this code can be reused.
AI.dly is a Flask backend combining AI chat, YouTube transcript summarization, PDF reading, web scraping, and translation into one API for a companion Chrome extension.
Mainly Python. The stack also includes Python, Flask, Together AI.
No license information was found in the README, so usage rights are unclear.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.