#langsmith

A reference implementation for learning and building AI evaluation systems.

Open-source enterprise AI agent platform for centrally governing agents, tools, memory, RAG, approvals, and durable workflows with FastAPI, LangGraph, LangChain, and LangSmith.

Build and operate production-grade AI agent systems through this 22-chapter technical course designed for collaborative learning with AI partners.

🚀 AI-powered Chrome Extension that generates context-aware LinkedIn comments using LangGraph multi-agent workflows, FastAPI, LangChain, and LLMGateway. Supports multiple comment tones, intelligent post analysis, and one-click comment insertion directly on LinkedIn.

AI Video Intelligence & Knowledge Synthesis Platform built with LangChain,LangSmith, ChromaDB, Whisper, and LLMs.

AccessLens — Production RAG system for EU Market Access intelligence. Synthesizes evidence from PubMed, ClinicalTrials.gov & OpenFDA across EMA, G-BA, HAS, AIFA and more. Hybrid search · Cross-encoder reranking · Claude-powered generation · RAGAS evaluation.

it's a agent that does the work of HR,IT and Finance ,implemented Rag based response and also done it using langchain and langgraph.

MCP-based AI agent monitoring system

An agentic Self-RAG system that answers biomedical research-verification questions using a LangGraph pipeline — retrieves from PubMed abstracts, grades its own retrieval, checks for hallucination, and abstains when evidence is weak.

AI support desk that routes complaints, drafts cited replies with hybrid RAG, and learns from every resolved case.

Local CLI to turn failed AI agent traces (wrong tool, bad args, over-refusals) from LangSmith/Langfuse into clean SFT/DPO fine-tuning data

LangChain application development with OpenAI and LangSmith observability.

Multi-agent AI customer support system — Pinecone hybrid RAG, SLA-aware ticketing, and RAGAS evaluation on FastAPI + Streamlit