Code agents

Forge: Empirically-validated multi-agent orchestration engine. Auto-designs swarms, guarantees interface alignment through contracts (+52.5% quality, 400+ experiments), real-time zero-dep monitoring dashboard. The first system combining auto-design + contract-first + live dashboard.

Learn API schemas from live traffic and generate OpenAPI specs. Analyze MCP/JSON-RPC agent sessions for wasted calls. Zero-infrastructure local reverse proxy.

🎨 Create stunning product marketing visuals and content effortlessly with our multi-agent system using the Swarms framework.

Use an LLM agent to automate ordering food and other items from Deliveroo, Uber Eats, DoorDash, etc.

Local-first RAG engine with cited answers from your own docs. GraphRAG, sealed sharing, MCP-native, VS Code Copilot integration. Nothing leaves your machine.

A powerful AI chatbot built with Streamlit and Groq API that combines text-based interaction, document processing, and vector search capabilities. Features include multi-format document handling (PDF, PPT, Excel) and intelligent model selection.

An AI-powered code reviewer supporting multiple programming languages, including: Python, JavaScript, Ruby, Java, SQL

Langchain agent that generates and executes Python code to interact with Airtable using the MCP code execution pattern from [Anthropic's blog](https://www.anthropic.com/engineering/code-execution-with-mcp).

LangGraph-powered conversational AI assistant — multi-turn memory, OpenRouter API, tool calling, OOP architecture. Live on Render.

🎓 AI-powered student productivity suite: convert docs to notes, manage timetables & todos, and chat with Isabella AI using a RAG-powered knowledge assistant. FastAPI + React + MongoDB + Gemini/LongCat/GPT/Microsoft/Mistral models.

A local multi-agent RAG system where four LangGraph agents (Planner → Retriever → Critic → Synthesizer) collaborate to answer research questions from academic PDFs, with real benchmark results: 87% RAGAS faithfulness, 22pp hallucination reduction via LLM-as-judge, and 0% failure rate under Locust load testing.

Privacy-first local RAG app — chat with your PDFs using Ollama (llama3) + LangChain + ChromaDB + Streamlit. 100% offline, no API key needed.

Local AI coder agent in langgraph. like lovable but works locally.

PickSmart AI-powered shopping assistant platform for personalized product recommendations implemented by Groq API, Tavily, Langchain, and Langgraph

ClassBuddy is a full-stack web application designed to enhance classroom collaboration, note sharing, and communication between students and teachers.

Tool-using GPT agent, equipped with Knowledge Base and ability to search using Google.

Developed a web application utilizing Streamlit, LangChain, and OpenAI's GPT model, designed to analyze, review, and enhance code quality, providing users with intelligent feedback and optimized code solutions.

An enterprise-grade, full-stack AI travel planner which provides data-driven itineraries for Lucknow, India and showcases production-ready architecture, combining a FastAPI backend with a Streamlit frontend. It leverages an advanced agentic RAG system, context-aware responses by integrating a local knowledge base with live, external APIs.

AI-powered CSV dashboard with chat-based data querying, auto-generated reports, and visual insights using FastAPI, LangChain & Gemini.

ScholarAI: multi-agent ai deep researcher built using langgraph and gemini-2.5 models

AI Chatbot powered by GPT-3.5-Turbo API by OpenAI. Complete with login functionalities and additional features using MySQL

Langchain Tool wrapped around Ionic SDK & OpenAPI Spec

Telegram bot that uses preset prompts to help users communicate like native English speakers.

Open-source context runtime and governance layer for coding agents. MCP server + Python SDK (Anthropic, LangChain, OpenAI Agents, Google ADK) with shared procedures, failure rescue, loop detection, cost tracking, and cross-vendor model routing across Claude Code, Codex, Copilot, opencode, and any MCP host.

Chat with MYSQL database

建立數位銀行RAG增強檢索的問答機器人

This repository are a series of demonstration scripts highlighting the functionalities of LangChain, a JavaScript library tailored for developing conversational AI applications. @ S. Leschev. Google Engineering Level: L6+

Blueberry - your personalized AI assistant. This was the stuff I made for a hackathon in college, which won 1st place :O

RAG model created in langchain using python to tune Gemini API and give it context through tokenization of pdfs into vectorization of the databases.

Hierarchical multi-agent customer support system built with LangGraph, Groq LLM, FastAPI & Next.js — featuring autonomous agent teams for analysis, research & quality review

MultiDocWebchat combines the functionality of a PDF document reader with a powerful QA bot for in-depth document exploration.

A LLM project to help researchers to find exact information from the research papers and articles.

Airline Reviews Chatbot App : The Airline Reviews Analysis app is a Streamlit application that leverages natural language processing (NLP) techniques, including GPT-3.5-turbo-0125 and Text-embedding-ada-002-v2, to provide answers to user questions based on provided context.

Practical workshop materials for a graduate-level course on Conversational Agents, taught at Université Côte d’Azur (Master’s in Artificial Intelligence, 2024-2025). This repo includes 7 sessions designed to teach students how to build, deploy, and evaluate conversational using Python, FastAPI, Langchain, and LLM focus on real-world use cases

Memory defense for AI agents — stops MINJA, AgentPoison, and MemoryGraft attacks. Zero dependencies.

Enterprise-ready AI agent template. FastAPI + LangGraph + RAG. Ship production agents in hours.

🛡️Secure and sandboxed API to execute Python code, upload files, install packages, and manage isolated sessions. Ideal for running untrusted code and ensuring application security.

CRM AI analytics for better decision making using a Text-To-SQL agent along with a medallion architecture and data science for statistical modeling

An Agentic AI Research Playground for building AI Agents and Mult-Agent systems leveraging open-source models, libraries, and frameworks. Models used to run agents locally on Nvidia RTX A2000 GPU - 8GB VRAM include the quantized Ollama models: llama3.1:8b-instruct-q8_0, llama3.1:8b_q8_0, qwen2.5:7b-instruct-q8_0, and qwen2.5-coder:7b-instruct-q8_0.

Design and develop your own AI chatbot with Streamlit! This session will guide you through setting up a chatbot interface, integrating a language model, and handling user interactions—all with minimal code.

Stone Scraper is an AI-powered tool for automated web data extraction. Built with Streamlit, Langchain, and Selenium to transform unstructured web content into clean, actionable insights. CURRENTLY WORKING ON OPEN AI API CLOUD DEPLOYMENT. Try it out ⬇️⬇️

Production-ready Retrieval-Augmented Generation (RAG) platform for intelligent log analysis, error diagnostics, and incident resolution. Built with LangChain and LangServe, the system provides an API-first, modular architecture designed for scalable observability and DevOps workflows.

Ask Manyu App to let users chat with multiple PDFs. Built with LangChain, OpenAI, Streamlit.

A chatbot that let you talk with your pdf file

FastAPI application with streaming Langchain agents and Tavily search tool

In this project I have built an end to end advanced RAG project using open source llm model, Mistral using groq inferencing engine.

Create examples for making Python web development to start easy.

An LLM based food recognizer web app which tell about details about food preset in image, calculates calories, fats etc

A curated collection of hands-on experiments, code snippets, and templates exploring the latest tools and frameworks in the Generative AI ecosystem

An open-source library for AI-native x402 integrations in the Solana ecosystem. Built for Python and Node.js, distributed via PyPI and npm, with server implementations for FastAPI and Express.js. Accelerate.

LLM Tool for effective test evaluation of ML projects with curated Checklists and LLM prompts

Multi-agent AI research assistant coordinating specialized agents with LangGraph. Leverages multiple research tools (Wikipedia, arXiv, etc ) with full LangSmith tracing for transparent reasoning. Delivers comprehensive scholarly answers through Groq-powered agents working in an orchestrated workflow, through a user-friendly Streamlit interface.

A RAG back and front end application

Pinecone Hackathon 2023: Codextranauts Team Repository.

Tired of searching information in the Spanish Tax Agency website? So do I! HaciendaGPT is you new friend!

Chat with Sql Server using google gemini generative ai

AI Cookbooks of Various Python Notebooks and code for using AI with various LLM models, UI's and Embeddings

REST API to generate summaries of news articles using a Large Language Model (LLM).

This is my repository for creating chatbots using various Machine learning techniques 🏆. From basic chatbots to Advanced 🔥. Continuously researching about new techniques.

AI-powered VSCode extension that uses LLM technology to provide insightful suggestions into code quality.

2Waffles.Ai - An innovative dual-powered, intelligent assistant AI CRM assistant designed to enhance the efficiency and effectiveness of customer relationship management operations.

Desktop application for managing Model Context Protocol servers (MCP). Provides a centralized interface to configure and manage MCP servers for use with LLMs and AI assistants such as Claude.

Enterprise LangChain platform with multi-agent collaboration, advanced RAG, local LLM support, and modern web interface. Production-ready AI orchestration for research, coding, and data analysis.

✨A gigachat-gigachain based AI research assistant💻📖

This is the backend of viewMo AI cloud platform. AI base graph generation engine, Agent base simulations, Protected endpoints with JWT token authentication and many more features included.

Winner 2025 – 1st Student Prize for the topic proposed by Le Mans School of AI

In this tutorial we will see 💡 How to get answers from a YouTube video using Chroma vector database, PaLM LLM by Google, and a question answering chain from LangChain. And finally, use Streamlit to develop and host the web application. You will need to use your google_api_key (you can get one from Google).

a Streamlit app with a chat interface , graph visualization, RAG, logging and so much more

《OpenAI API와 파이썬으로 나만의 챗GPT 만들기》 (2024년 4월 출간) 예제

Grimoire (gʀiˈmwaːʀ), a book (tool) of magical knowledge about your code and its dependencies.

This is a minimal demo project to show the capabilities of a Text2SQL system using LangChain, it contains all the things you required to build a basic RAG system. Using Chinook as the sample database.

MoodSense AI: A transformative journaling app built with Next.js, Tailwind CSS, and Langchain, leveraging the power of AI to analyze emotions and provide valuable insights.

Advanced local-first RAG system powered by Ollama and LangGraph. Optimized for high-performance sLLM orchestration featuring adaptive intent routing, semantic chunking, intelligent hybrid search (FAISS + BM25), and real-time thought streaming. Includes integrated PDF analysis and secure vector caching.

Filling in the missing gaps with langchain, and creating OO wrappers to simplify some workloads.

Best way to intergrate Code Interpreter and llm-based agents to your work

Local LLM infrastructure for distributed AI applications. Serve Ollama-powered models across your network

Track, visualize, and optimize LLM API spending. Monitor OpenAI & Anthropic costs per feature, detect waste, suggest savings. Zero-config Python profiler.

RAG-Complete-Cook-Book is a practical guide and code collection for building Retrieval-Augmented Generation (RAG) pipelines. It provides step-by-step Jupyter notebooks and Python scripts covering the entire RAG workflow.

🔀 One prompt in. The right model out. Open-source LLM router with 100% routing accuracy, 47+ providers. Budget enforcement, semantic cache, intelligent failover. Zero ML, 19.5KB. MIT.

Build an AI Chatbot to chat with any PDF

The Web application contains two UI. One for Quant developers who make Trading algorithms and second UI is a chatbot for derivative traders. After posting algorithms, they are stored in vector databases and later with help of langchain and OpenAI Apis, the LLL is trained. Later using LLM, chatbot replies traders with condition specific Algorithms.

RAG technique for QA tasks with PDF, website and video, leveraging LLMs and the OpenAI API for interactive applications

AI integrated Job Searching Website

Welcome to GenAI_DayZero, a hands-on journey into Generative AI and Large Language Models (LLMs). This repository showcases my learning and experiments, from zero knowledge to advanced AI tools. I’ll be sharing code, insights, and resources to explore the exciting possibilities of GenAI. Let’s learn and build together!

RAG система, которая предоставляет точные и обоснованные ответы на юридические вопросы, основываясь на актуальном российском законодательстве.

Code examples implemented with different AI frameworks (Vercel AI SDK, Mastra, Langchain.js, Genkit) to compare them and decide which one to choose for next projects

Browse memories, query context, and run AI agent workflows directly from VS Code.

Experimental RAG that consumes Cyber Security articles via RSS

Research: LangChain, Titanic SQLite Database, and the API of OpenAI

具备长期记忆和实时流式响应的 AI 聊天助手，基于 LangGraph + Flask + SSE 构建

Fitlog is a GenAI-powered workout tracking application that allows users to log their routines, workouts, and sets. The app includes features like fuzzy search for routine and workout names, powered by Fuse.js, and integrates Prisma for database management. This is a MERN-stack application built using Next.js for server-side rendering.

A short python file showcasing how a speech-to-speech chatbot can be generated with only a few lines of code and an OpenAI API key.

An agentic chatbot to answer questions regarding a hotel's information and database.

Source code for Kagi Challenge

An LLM-powered web app to help developers brainstorm and kickstart new software projects!

Rasa LLM Community Challenge

This repository contains code for a Telegram bot that uses GPT-based language models to generate responses to user queries. It includes a Python script for creating a vector index based on a corpus of text files, and another script for running the Telegram bot. Users can add their own text files to the data folder and use the bot to generate respo

Implementing LangChain concepts and building meaningful stuffs

骆驼电影侦探社（服务端）

A Multi-modal chatbot with LangChain, that supports RAG, Paperswithcode, and Image generation using Dall-E-3