Production-Ready MCP Server Framework �� Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents

Discover, run, and compose AI agents from any framework.

Research workflows made easy, locally and in the Cloud.

MatDesign: a programming-free AI platform to predict and design materials

MCPcat is an analytics platform for MCP server owners 🐱.

Emotion AI (Sentiment Analysis) of Tweets using TextBlob and Django (Python)

Contains code to demonstrate distributed training in TensorFlow 2 with AI Platform and custom Docker contains.

Official SDK for the Maybind Digital Twin Platform — interact with AI twins via a powerful API.

Deploy FastAI Trained PyTorch Model in TorchServe and Host in GCP's AI-Platform Prediciton.

Train Magenta DDSP Autoencoder on Google Cloud AI Platform.

A framework that allows Detectron2, AdelaiDet, and D2Go training and evaluating on GCP's AI platform.

Cluster and plot S-BERT embeddings generated from song lyrics

SnifTern.ai is an AI-powered platform that detects fake internship postings and verifies company legitimacy using advanced machine learning. Features real-time fraud analysis, multi-platform integration (LinkedIn, Indeed, Glassdoor), PDF reports, and multi-language support to protect students from internship scams.

🐻🎷 Scalable Machine Learning (Recommender System) with Apache Beam, Google Dataflow and TensorFlow

A simple CLI dashboard to track your running AI Platform jobs, their progress and status.

Open source platform for the machine learning lifecycle

AI-powered dashboard for forecasting vegetation and wind patterns using machine learning. Supports real-time sensor simulation and adaptive climate response insights.

A Flask-based learning platform that uses AI to generate personalized learning paths and content. The project has been reorganized with a clean architecture and uses free online LLM services.

AICoreDirector - an enterprise AI governance & Orchestration platform. it unifies all LLM calls, AI components, and traditional ML services behind a single interface. It provides intelligent routing and scheduling, fallback, and integrated management—serving as the enterprise AI capability bus and central hub for production.

Scalable AI inference platform with FastAPI, Celery, Redis, Postgres, Nginx, Prometheus, Grafana, and Docker. Supports asynchronous ML tasks, persistent analytics, monitoring, and observability in a production-ready architecture.