Langchain agents

Projet issu du codelab Devoxx France 2025 “À la recherche du RAG perdu” : atelier de 3h pour apprendre à créer un chatbot IA Générative autonome, local et sans Internet, basé uniquement sur des frameworks open source

An elegant article writer assistant that creates (almost) ready for posting articles providing main ideas from the user, built with langchain

langchain agent，chatglm，neo4j实现movie qa。

Multi-Modal Next.js Chat App with Vercel AI SDK & LangGraph.js

Biq Query + langchain REST API written in python

This is a test version of the agent_toolkit in langchain. Please do not use it in production.

Easily build and operate generative AI applications. Create Assistants API and GPTs based on any LLMs.

Javascript RAG Chatbot with Langchain, OpenAI and Supabase vector store.

AI YouTube Video Chat application, to ask questions to a YouTube video bot and get answers.

Inquiry videos with ChatGPT

A chatbot created with Next.js and AI SDK, using Langchain with RetrievalQA to provide information from a PDF loaded into a vector store in MongoDB.

This project combines Azure AI Search, Azure OpenAI Service, LangChain, React.JS, and Python FastAPI to create an intelligent system for managing Jira issues. It features advanced AI search for seamless document retrieval, a user-friendly React.JS front-end, and a robust Python FastAPI back-end.

Question Answering Generative AI application with Large Language Models (LLMs), Amazon Bedrock, and Amazon DocumentDB (with MongoDB Compatibility)

Developed a web app using LLM models, Langchain, and chatbots for PDF interactions. Users upload PDFs and ask questions, receiving instant chatbot responses for efficient content retrieval.

Say goodbye to endless Google searches and hello to our clever chatbot, the ultimate Wikipedia companion for all your Q&A needs.

This project aims to provide an efficient and scalable API for embedding and storing vectors, leveraging the power of FastAPI, Langchain framework and a vector database such as Chroma.

Built with Gemini API, LangChain, Chainlit, and Python, this multimodal assistant explores AI tool integration driven by curiosity about multimodal capabilities. It demonstrates modern AI development by combining cutting-edge multimodal AI with practical user interface design.

LangChain Text Summarization and Image Generation

SFEIR School Langchain

Implementation of Reflective RAG, Self-RAG & Adaptive RAG tailored towards production-oriented applications with LangGraph and OpenAI API

This project is Genratve AI and AI-powered content generation tool that leverages Hugging Face's models to create customized content based on user queries. The application is built using Streamlit and provides an interactive UI for generating content tailored to different age groups and task types.

Notebooks demonstrating vector search & RAG design patterns with Redis Python clients.

此存储库展示了用于检索增强生成（RAG）系统的各种先进技术。RAG 系统将信息检索与生成模型相结合，以提供准确且上下文丰富的响应。

This project aims at giving the best customer service ever using the power of LLM models like GPT.

use 🦜️🔗 to communicate with varied files & web

Sync your team's data to your LLM applications in real-time

Enhance your CLI with AI - Using Langchain Framework & OpenAI Functions Agent

This project demonstrates how GenAI can potentially be leveraged in financial and investment advisory services to provide personalized and tailored recommendations and strategies.

A small interactive game with an LLM that generate (not random ;) ) events and actions that you need to follow in order to win !

Hybrid Knowledge Agentic RAG System

Virtual-Assistant LLAMA2/OpenAI with specific knowledge (RAG) in gradio UI.

Scrapes headlines from CNN and FOX, then has ChatGPT do cross-analysis

A systematic framework for converting n8n workflows to LangGraph implementations using a three-phase orchestration process. Includes production requirements analysis, custom logic extraction, and automated LangGraph code generation.

This is a simple lab I have implemented to test Knowledge Augmented or Retrieval Augmented Generation (RAG) with Large Language Models. In particular, I am using LangChain, Streamlit, and OpenAI ChatGPT API.

Langchain 🦜 running🏃‍♀️ on express including file reader and history management

A set of AI tools to automate resume scoring and generate interview questions.

End-to-end deployment of a scalable RAG chatbot utilizing LangChain for retrieval-based QnA. The project leverages robust CI/CD practices integrating MLFlow with emphasizes on cost analysis.

Understanding any codebase. Enter the github repo's url and chat with the codebase.

Use OpenAI and LangChain to automatically visualize tabular data.

A dynamic learning assistant designed to simplify the onboarding and training process for new hires. Users can upload documents or enter URLs for training materials. Built with Spring Boot, @Langchain4j and spring-ai

Runtime kill-switch for autonomous AI agents. Regime-aware Bayesian governor, NL policy compiler, adversarial red-team simulator. AGPL + commercial.

An AI-powered branding assistant that generates brand name, slogan, and concept visuals from a simple description.

🦜️🔗📺 A langchain summarizer for YouTube videos.

Open Source OpenTelemetry-native Observability tool for GenAI and LLMs designed to provide developers with complete capabilities for monitoring, analysing, and optimising LLM applications.

A roadmap to AI Engineering excellence: Masterclass in Generative AI, RAG, and Agentic Systems with a focus on scalable and production-ready architectures. 🚀🤖

Nautobot AI Plugin - Large Language Models (LLM), Model Context Protocol (MCP), Middleware and Dynamic Prompts powered by Langchain Ecosystem.

Muiti-Agents System for Software Engineering built by LangGraph, with interactive Workflow of WebUI.

Retrieval Augmented Generation (RAG) engine for intelligent document analysis. integrating LLM, embeddings, and vector database to extract, summarize, and query insights from multi-format documents.

A modern LangChain tutorial. v0.2 based

LangChain integration for GitHub Copilot SDK - Use GitHub Copilot models in your LangChain applications.

《OpenAI, 구글 Gemini, 업스테이지 Solar API를 활용한 실전 LLM 앱 개발》(2025년 1월 출간) 실습 코드

Introducing ChatGPT tailored for every website. Seamlessly address your visitors' queries using a customized chatbot, trained directly from your website's content. An excellent substitute for platforms like Chatbase, SiteGPT, and Dante AI.

Pharmaceutical Insight Retrieval System designed to help users gain meaningful insights from research papers and documents in the pharmaceutical domain.

Athena's Oracle: Enlightening AI for Document Insight and Discovery AI 驱动的文档洞察引擎

4 chatbots with memory made with Langchain, VertexAI and Gemini, as a cyber challenge to capture and expose RAG content.

An advanced, fully local, and GPU-accelerated RAG pipeline. Features a sophisticated LLM-based preprocessing engine, state-of-the-art Parent Document Retriever with RAG Fusion, and a modular, Hydra-configurable architecture. Built with LangChain, Ollama, and ChromaDB for 100% private, high-performance document Q&A.

Coordination intelligence for any agent system

Datadog for AI Agents — Distributed tracing & observability for multi-agent systems. Trace every LLM call, tool use, and agent decision with 2 lines of code. Beautiful TUI + Web dashboard. Zero-config instrumentation for OpenAI/Anthropic/LangChain.

YAML-first, domain-driven data governance for AI agents — teach agents your business domains, metrics, and rules before they write SQL

OpenAnyWork is the flagship desktop workbench for deepagentsjs. It's more than just a chat window; it's a productivity tool for "deep agents." By integrating file system access, Docker isolation, the MCP protocol, and a powerful sub-agent system, OpenAnyWork enables AI to truly perform complex tasks on your computer.

Learning to build LLM from scratch, following rasbt/LLMs-from-scratch footsteps.

Conversational AI assistant for Good Health Clinic

AI Engineering: Annotated NBs to dive into Self-Attention, In-Context Learning, RAG, Knowledge-Graphs, Fine-Tuning, Model Optimization, and many more.

CrewAI Agentic AI Framework Build smart, role-based AI teams with CrewAI!, Agents collaborate like real teams to solve complex tasks. from DevOps pipelines and secure auth flows to content creation and business automation. Easily customizable, extendable with tools, and fully powered by GPT-4 + Python 3.11.9.

A comprehensive, versatile AI system built with NestJS that provides specialized AI agents capable of performing various tasks through real AI integration, background processing, and system automation.

Agentic -powered synthetic data generator that creates flowcharts using LangGraph orchestration. Features FastAPI integration, OpenAI LLM processing, and automated Mermaid diagram generation.

Generative AI Practices and Mini-Projects: A hands-on repository for Generative AI mini-projects! Explore model building, fine-tuning, and RAG techniques. Includes experiments with open-source models like LLaMA and Gemma, plus deployments using OpenAI and Google Gemini APIs.

AI-powered mock interview simulator with coding, tech, and HR rounds using FastAPI, LangChain, and MongoDB.

Persistent memory and identity for AI agents. Free hosted API.

Demo code and presentation materials for the talk "Bug Bounty Hunting with AI Agents" at Basel One 2025.

This is the repo where you learn ai agents and ai llm application

Full-stack RAG template: FastAPI + LangChain LCEL + Next.js 14. Multi-KB retrieval, hybrid search (dense+BM25/RRF), FlashRank reranking, SSE streaming, RAGAS evaluation & JWT auth. MySQL + Chroma + MinIO.

PropertyLoop Real Estate Assistant: An AI-powered chatbot with multi-agent architecture that helps landlords, property managers, and tenants with property issues, tenancy law, and maintenance through smart image analysis and regional-specific guidance.

自然 ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool chain compositions via knowledge graph analysis, detects execution-level side effects (not just text output), and runs multi-phase trust exploitation campaigns that model real attacker behaviour.

Docker image to run an Ollama local LLM server. Secure by default, all API requests require a Bearer token (auto-generated on first start). OpenAI-compatible API. Supports first-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Multi-arch: amd64, arm64.

The .cv open file format - spec, SDKs, viewer, CLI, server middleware

基于 Spring Boot 3 + LangChain4j + Vue 3 构建的智能物流客服助手。集成 RAG、多模态交互、流式响应及基于 MongoDB 的对话记忆管理，旨在提供高效的自动化客户服务体验

🐉 ThingsBrain 是基于 Dante Cloud 企业级能力构建的，一款兼容阿里云物联网平台标准、支持 MQTT 动态认证与 OAuth2.1 安全体系的高扩展性物联网平台。具备多协议、多存储可插拔架构，为万物互联与 AI 融合提供高可靠、高安全的一站式物联网应用基座。也是 Dante Cloud 全栈能力的最佳价值兑现应用场景。🔝🔝 点个star 持续关注更新！

OpenSpawn — An open source multi-agent coordination platform

Evidence-synthesis RAG assistant for TCM practitioners — hybrid vector + knowledge graph retrieval over 17 classical texts, with query classification, self-critique verification, and blind A/B arena evaluation.

一个 简单的 AI 投资助理，管理股票（美股、港股）和基金（国内基金），同时具备类似 Hermes 自迭代学习的能力

Chrome DevTools for AI Agents - Real-time debugging, pause, inspect, and step through your AI agent execution. Auto-instruments OpenAI, Anthropic, LangChain.

Long-term memory layer for AI agents

OS-enforced sandbox backend for LangChain Deep Agents using Landlock (Linux) and Seatbelt (macOS)

RAG-Powered Financial Query Assistant for JPMorgan Chase documents with Hybrid Search, Docker support, and Streamlit UI

EduMIND — Multimodal Bilingual Lecture Assistant with Anti-Forget RAG, Whisper ASR, VietMix NMT (CMI-aware), and Human-in-the-Loop Active Learning via Label Studio. Built for code-mixed Vietnamese–English academic environments.

A comprehensive, end-to-end learning path for Retrieval-Augmented Generation — from core concepts and document processing to agentic RAG systems, evaluation, and production deployment.

Production-ready Neuro-Symbolic AI & GraphRAG-powered Multi-domain Expert System. Hybrid forward/backward chaining inference engine over Neo4j Knowledge Graph + Qdrant Vector DB, operating across Chemistry, Plane Geometry, and Algebra domains via FastAPI & Streamlit.

Live-updating index of LLM agent frameworks shipping on GitHub, refreshed every 15 minutes

jitknow，企业级可私有化部署的AI知识库

An open-source visual debugger for multi-agent AI, featuring local replay, loop detection, and trace branching.

A hands-on LangChain course with 100+ runnable labs — RAG, tools, agents, MCP, structured outputs, and multi-provider LLM support.

A Langchain integration for FalkorDB

Multi-agent medical assistant for medical Q&A, RAG, web retrieval, and medical image analysis with human review.

TypeScript AI agent framework — 40+ LLM providers, 100+ tools, multi-agent orchestration, RAG, guardrails, circuit breakers, HITL, budget enforcement. Open-source CrewAI / LangChain alternative. — For Building Production-Grade Multi Agents in Minutes at Scale

Praison is a production-ready framework for building multi-agent AI systems that enables intelligent agents to collaborate, reason, self-reflect, and use tools to automate tasks, with support for over 100 LLMs and flexible workflows for both code and no-code usage.

Evidence-driven AI software synthesis and verifiable artifact delivery platform with stateful orchestration, layered memory, hybrid retrieval, build validation, and reproducible deployment.

LLM 修仙之路 — 打怪升级式 LLM 技术栈学习平台:内置 IDE、Docker 沙箱、8 章 39 任务,从 API 调用到自建小模型 / A gamified LLM learning platform

An application that uses a multistage pipeline to remove any watermarks from AI generated text

A multi-agent AI research pipeline built with LangChain and GPT-4o-mini. A search agent gathers sources via Tavily, a reader agent scrapes the most relevant page, a writer chain drafts a structured report, and a critic chain scores it, all wrapped in a Streamlit UI. Built for learning multi-agent orchestration