Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.

A Python package to assess and improve fairness of machine learning models.

Official implementation of Meta Prompting for AI Systems (https://arxiv.org/abs/2311.11482)

Practical system design, tools, and hands-on resources for building Gen-AI agents & agentic AI systems.

IdenProf dataset is a collection of images of identifiable professionals. It is been collected to enable the development of AI systems that can serve by identifying people and the nature of their job by simply looking at an image, just like humans can do.

An innovative AI system developed to extract actionable insights by converting natural language into SQL queries via Google's Gemini model and dynamically visualizing the data with Plotly Express, streamlining decision-making across all levels of expertise.

Saturn accelerates the training of large-scale deep learning models with a novel joint optimization approach.

Resources for recent AI systems (deployment concerns, cost and accessibility). -- closed

Learn Agentic AI using Dapr Agentic Cloud Ascent (DACA) Design Pattern and Agent-Native Cloud Technologies: OpenAI Agents SDK, Memory, MCP, A2A, Knowledge Graphs, Dapr, Rancher Desktop, and Kubernetes.

🧾 Open, hands-on AI education program — from Machine Learning to Generative Intelligence. Weekly lessons in Jupyter Notebooks, ready for Google Colab.🧾

Organize your AI agent teams with the Viable System Model. The missing organizational layer for multi-agent systems.

Welcome to the repository for **Exercise 3 of the AI Systems Course** at the **University of Tehran**. This project focuses on designing and implementing a lightweight, efficient **processing element (PE)** for performing operations of neurons in a **multi-layer perceptron (MLP)** using Verilog.

Prototype for Block, a new LLM-multi instance scheduling Framework

This project uses AI-powered vehicle detection to enable customizable and efficient parking space management.

Algorithmic inspection for trustworthy ML models

Source repo for the blog post Stop Stuffing Your System Prompt: Build Scalable Agent Skills in LangGraph

Main entry point to the TrackieWay Project, with the entire ecosystem

A Startup Execution Operating System that turns ideas into live, measurable systems in 24 hours using architecture, workflows, automation, analytics, and decision engines.

Open Potatoe is a deterministic AI agent runtime designed for reliable task execution with LLM planning and structured system control.

Replay + diff for AI decisions. Deterministic, audit-first workflow kernel.

DeterminAI is a deterministic, transactional AI execution engine that provides immutable, event-sourced workflows for AI systems.

A multi-agent AI system for data analytics, insights, and smarter decision-making.

Гибридная модель ИИ для автошахмат, сочетающая формальные эвристики и адаптивное поведение.

a Go-based library and runtime for building intelligence systems 🧠

Welcome to my digital garden where I cultivate thoughts on Machine Learning, Generative AI, Trustworthy AI, AI Systems, Efficient AI, and Paper Reviews.

AI-powered decision intelligence engine for retail margin risk prediction

A local control plane for Model Context Protocol (MCP) servers — unify stdio and HTTP MCP tools behind a single, secure local endpoint.

LLM System for Pharma marketing agents

Лабораторные по дисциплине "Системы искусственного интеллекта", ИТМО.

AI systems builder focused on behavioral AI, marketing intelligence, and decision automation.