python

Record and transcribe Teams, Zoom, and Google Meet calls locally with AI-powered speaker identification. Open-source alternative to Evaer, Otter.ai, and Fireflies. Offline speech-to-text using Whisper — no cloud, no subscriptions.

Extract the most viral clips from a random youtube video.

From-scratch voice agents in Python: end-to-end speech pipelines, runnable chapters, and a small shared library. Local models, explicit streaming behavior.

Local-first CLI that reads your Spec-Driven Development artifacts and recommends the best value-for-money AI model to implement them. Powered by Ollama — your specs never leave your machine.

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

In this project, several approaches for training/finetuning an audio gender recognition is provided. The code can simply be used for any other audio classification task by simply changing the number of classes and the input dataset.

A framework for hosting and scaling AI agents.

A collection of Voila web apps for geospatial applications

An end-to-end image captioning project using a CNN encoder (ResNet-50) and LSTM decoder in PyTorch. Includes vocabulary building, preprocessing, training with BLEU evaluation, and inference. Generates natural language captions for images with saved metrics, model checkpoints, and visualization outputs.

Free, open-source AI video caption generator. Add trending animated subtitles to any video — 6 styles (Hormozi, MrBeast, Karaoke), word-level animation, 100+ languages. Powered by Whisper + FFmpeg. Self-hosted with Docker.

AI commit messages from your local LLM - Ollama / llama-cpp backed, offline, Conventional Commits, with review + changelog modes.

A CLI-first AI code review tool for git diffs and CI workflows. Analyze changes with relevant codebase context using local Ollama models or cloud LLMs.

AI assistant built with Streamlit, NVIDIA NIM (LLaMa 3.3:70B) / Ollama, and Model Control Protocol (MCP).

An AI-powered interactive web application built with Streamlit that predicts whether a candidate will get placed in a job (or admitted) based on academic performance and other features.

An AI-powered chatbot that leverages RAG (Retrieval-Augmented Generation) to answer your questions based on the content of uploaded PDFs

An interactive RAG agent built with LangChain and MongoDB Atlas. Manage your knowledge base, switch embedding models, and tune retrieval parameters on-the-fly through a conversational interface.

Quick start. Index multiple documents in a repository using HuggingFace embeddings. Save them in Chroma and / or FAISS for recall. Choose OpenAI or Azure OpenAI APIs to get answers to your questions - Q&A with OpenAI and Azure OpenAI.

Upload & Merge CSV or JSON Data with Images to Notion Database

ONNX implementation of the BGE-M3 multilingual embedding model and tokenizer with native C#, Java, and Python implementations. Generates all three embedding types: dense, sparse, and ColBERT vectors.

A reusable, open-source AI infrastructure designed for communities and organizations. It understands structured data, processes official announcements, and answers questions accurately by centralizing important information.