langsmith-tracing

Learn GenAI and Agentic AI from Zero to Production

Agentic AI framework built using LangGraph and Multi-Agent Control Plane (MCP) for building structured, goal-driven multi-agent systems.

Revolutionary AI ETL with Medallion Architecture: Zero-touch autonomous & HITL pipelines on Databricks

🔍 AI observability skill for Claude Code. Debug LangChain/LangGraph agents by fetching execution traces from LangSmith Studio directly in your terminal.

🤖 CodeForge AI: An autonomous multi-agent coding system powered by LangGraph for agentic software development and automated workflows. SOTA custom agentic GraphRag, shared-state memory, auto-model routing for cost optimization, and a range of custom tooling.

Distributed, cloud-native fraud detection: Kafka Streams + XGBoost + LangChain Agents + ChromaDB RAG + River Online Learning, a self-improving pipeline, deployable on Docker Compose or GKE

MCP server for LangChain, LangGraph & DeepAgents knowledge + LangGraph agent debugging (Polly-like)

Successfully developed a state-of-the-art AI-driven credit underwriting engine using LangGraph and FastMCP that orchestrates multiple specialized agents to evaluate risk, detect fraud, and generate explainable credit decisions, delivering transparent, auditable, and tailored financial solutions with unmatched efficiency.

a self-improving analytical agent grounded in reflection design with external feedback to refine responses.

An Advanced Retrieval-Augmented Generation (RAG) system powered by a Knowledge Graph + Neo4j + Cypher-based retrieval + Review loop architecture.

Production-grade multimodal RAG backend — async document ingestion, 4 retrieval modes, agentic generation with guardrails, powered by FastAPI, LangChain, and Supabase pgvector.

Job Interview Notification AI Agent (LangGraph JS)

Intelligent Document Assistant with LangSmith (RAG)

LangGraph JS app based on CoinMarketCap API

A Python-powered web scraping tool with built-in article summarization, CLI and API interfaces, and Docker support. Ideal for extracting and managing web content at scale.

An autonomous travel planning agent that creates full itineraries (flights, hotels, activities) using LangGraph and real-time Amadeus API data ✈️

LangSmith tracing plugin for opencode — captures sessions, LLM calls, tool calls, reasoning, and context compaction. Trace taxonomy compatible with langsmith-claude-code-plugins.

Self-correcting RAG pipeline with LangGraph — evaluates retrieval quality and falls back to web search when local docs aren't enough.

Q&A chatbot built with LangChain and Ollama, featuring LangSmith tracing for monitoring conversations.

RAG on PDF documents without a vector database. Uploads are indexed into a hierarchical document tree via the PageIndex API — at query time, Llama 3.1 (Groq) walks the tree to select the most relevant sections, then generates a grounded answer from their full content. Includes a FastAPI backend and a simple web UI.