A complete LangGraph guide for PhD students and researchers. From zero to multi-agent systems with Python examples (chatbots, ReAct agents, supervisor patterns, research pipelines).

Agent orchestration engine built on a Cyclic State Graph

Prism-inspired multi-agent orchestration framework built on LangGraph. Security-first, provider-agnostic, composable.

LangGraph supervisor with parallel specialist agents. 1.99x speedup vs sequential multi-agent, reproducible in 6s with no API key. Planner, retrievers, analyzers, verifiers, synthesizer.

A comprehensive multi-agent AI system built with LangGraph and Google Gemini. Features specialized agents (Coder, Enhancer, Researcher, Validator), RAG implementation, ReAct pattern, and supervisor orchestration. Includes data analysis, document drafting, and conversational agents with quality validation.

Supervisor-orchestrated multi-agent content pipeline (LangGraph) with 4-way LLM fallback (Gemini/Groq/OpenRouter/Cerebras), bounded revision loop, and a Streamlit UI.

Enterprise-grade multi-agent AI orchestration framework featuring supervisor-driven workflows, reviewer governance, structured execution state, and autonomous software delivery patterns.

A production multi-agent supervisor pattern app built with OpenAI Agents SDK, Next.js, FastAPI, and ChromaDB — featuring live agent status, RAG pipeline, and full delivery package export

Production-grade hierarchical multi-agent system with LangGraph — parallel specialist agents, HITL approval gates, safety pipeline, and fraud risk assessment workloads

🔴 CMatrix-RED is an agentic red-team platform for running controlled, human-in-the-loop security simulations across modern applications and infrastructure. It combines multi-agent orchestration, approval gates, monitoring, and audit-friendly workflows to help teams test defenses safely, repeatably, and at scale.

Capstone: Multi-Agent AI Platform orchestrating specialized agents for complex task solving

Rahnuma is a source-grounded Agentic AI admissions advisor for Pakistani students, built with LangGraph, FastAPI, pgvector, and Next.js. It combines cited prospectus retrieval, deterministic university merit calculations, persistent student profiles, live web fallback, and human-confirmed profile updates

🛡️ CMatrix is an agentic red-team platform for running controlled, human-in-the-loop security simulations across modern applications and infrastructure. It combines multi-agent orchestration, approval gates, monitoring, and audit-friendly workflows to help teams test defenses safely, repeatably, and at scale. Built with FastAPI, Next.js, Docker.

A FastAPI application that runs a finance analysis agent to analyze stock tickers using a streaming agent runner and various data tools (yfinance, Pinecone, sentiment analysis, etc.).

Production-grade multi-agent AI system with LangGraph supervisor pattern, RAG knowledge base (ChromaDB), and Anthropic Claude — routes queries between specialized triage, scheduling, and eligibility agents