Code agents

This is a AI Agent developed during a college project for the Machine Learning class. It is trained using the PokeAPI with the PokeBase library from Python and RAG documentation provided by Bulbapedia.

SmartRAG is a terminal-based RAG system using LangGraph. It processes queries by retrieving relevant content from markdown or PDFs, then responds using OpenAI GPT. Supports webpage-to-PDF conversion, vector DB search, and modular flow control.

On-Premise AI Powered Research Assistant Right In Your Terminal

In this repository, you'll find a collection of well-structured code examples, exercises, and explanations to help you effectively interact with OpenAI's GPT-3.5 model and Langchain using JavaScript.

The AI agents include a researcher, a chief editor, and an HTML writer. The researcher will gather the latest news on a specific topic, the editor will select the best one, and the HTML writer will create an HTML template for the newsletter.

AI Data Science Tutor powered by Google Gemini 1.5 Pro Latest offers multi-chat support, persistent memory, voice-to-text input, and IP banning for security. Users can create, rename, and delete chats, ensuring a seamless, secure, and intelligent AI-powered Data Science learning experience. 🚀

NewsBot is an AI-powered Q&A tool that answers questions from uploaded PDFs or web article URLs using LangChain, OpenAI, and Streamlit.

Web application to help develop scraping techniques to create context in LLM prompts.

Meet MySQL Assistant: Access database info seamlessly with natural language. No SQL expertise required. Simply ask questions, receive clear responses.

Safe Agentic Browsing. Assess target URLs for potential threats and alignment with the agent's browsing intent before navigation.

OdiaLingua is an innovative AI-powered chatbot platform designed to preserve and promote the Odia language. It features natural conversations, real-time information, and authentic text-to-speech capabilities, making Odia language accessible through modern technology.

Financial Analysis Agent that can get accurate data for a selected company and perform fundamental and technical analysis

LLMOps API 是一个基于 Flask 的 API 服务，用于构建、管理和部署基于大语言模型的智能体应用。该项目集成了 LangGraph 和 LangChain，提供了一套完整的工具链，用于创建具有状态、多角色的智能体应用程序。

This project implements an Agentic RAG (Retrieval Augmented Generation) Chatbot, initially accessible via a web interface. The bot's primary role is to serve as a genuine and professional company assistant, capable of engaging with clients, understanding their needs, and effectively guiding them towards purchasing our services and products.

An Open source version of FileQueryBot. Unleash the power of conversational AI on any document. Upload or link files in any format - PDF, TXT, PPTX, DOCX, and more - and let FileQueryBot answer your questions with precision and ease.

无需编程，即可快速构建基于先进AI模型的各类智能应用——从简单的问答机器人到包含复杂逻辑的工作流。构建完成后，一键发布 至主流社交平台、Web网页，或通过开放API无缝集成到现有系统进行深度开发。

GraphRag based chatbot built using LangChain and Neo4j, designed for hospital systems. The chatbot retrieves structured and unstructured data about patients, visits, physicians, insurance payers, and hospital locations. This project also explores integrating graph databases and deploying the chatbot using FastAPI & Streamlit

A Typeform-inspired Chat Feature with Chat Agents for Engaging Data Collection, Powered by AutoGen and Langchain. Includes REST API Integration for Messaging Systems.

RAG (Retrieval-augmented generation) app made with Flutter, Firebase, Gemini, LangChain and Pinecone.

Claude Code Agents offer specialized AI agents for code, localization, architecture, and automation. Build review and tailor agents for tasks with trust 🐙

SQL Agent powered by LLMs

Rag Tools for Retrieval QA

TravelGenie is a full-stack AI-powered travel assistant that helps users effortlessly plan end-to-end trips through a conversational interface. Built with FastAPI (backend) and TypeScript + Tailwind (frontend), it uses multi-agent orchestration to deliver intelligent travel suggestions.

The News Summarization & Fake News Detection App is an AI-powered solution I developed to make information consumption smarter and more trustworthy. Built with FastAPI, LangChain, HuggingFace, and FAISS, this application retrieves the latest news articles based on any user query

Record voice, transcribe a prompt, picturize the prompt, create variations, get description of a celebrity and upload, other use cases on KB

This project is an automatic web scraper that uses the LLM Ollama gpt-oss:20b to parse the body content of a web page. The application is built using Streamlit for the user interface and various Python libraries for web scraping and parsing.

AI-powered health & nutrition app offering personalized care, meal plans, baby tracking, pregnancy support, and smart hospital location services.

🚀 Build a production-ready Agentic RAG system with LangGraph using minimal code and streamline your AI development process.

We will use langchain and OpenAI to create prompts, scrape web for a given user, find the linkedIn profile, grab the information from the linkedin profile and build a persona around that individual. It will help you to get an idea of who someone is in brief. Thier interests, thier profession.

基于LangGraph构建的智能体系统，通过FastAPI暴露OpenAPI接口，实现智能体编排功能。

ContextAgent is a production-ready AI assistant backend with RAG, LangChain, and FastAPI. It ingests documents, uses OpenAI embeddings, and stores vectors in ChromaDB 🐙

Fine-tuned Llama 3.1 8B · QLoRA · RAG serving stack · FastAPI · Pinecone · Azure

🚀 Community-driven Naver integrations for LangChain! Seamlessly connect Naver's search, translation, and AI services with LangChain to build powerful AI-driven applications

Application that turns into a Chat-Bot by entering the OpenAI API Key and Prompt.

Your Study Copilot 🤖; A Comprehensive Suite of AI-Powered Study Assistants.

a LangChain SQL Agent that enables intuitive interaction with SQL databases

Sample project to connect Microsoft teams via (Power Automate) to Google Vertex AI project

Click below to visit my website

Using CrewAI and RAG to build a senior high school QA System and leetcode solver

Repo-gniton is an intelligent tool that helps developers understand, navigate, and work with code repositories. It dynamically ingests GitHub repositories, parses code and documentation, and prepares them for retrieval and AI-powered assistance.

A RAG App on Self hosted kubernetes platform

PulsarWave: An ML and NLP-powered tool for highlighting key trends/insight in news feeds data.

LangForge is a comprehensive documentation platform for LangChain and its ecosystem, providing detailed guides, API references, and interactive examples for building with large language models (LLMs).

Advanced semantic text chunking with custom structural markers, whole-text coherence preservation, and flexible token management. Features async processing, LangChain integration, and dynamic drift detection. Ideal for RAG systems, augmented text processing, and domain-specific document analysis.

An interactive Tic-Tac-Toe game where three AI agents work together using CrewAI as the agent framework and MCP for distributed communication.

Manage Notion tasks efficiently with CrewAI using an agent-driven workflow.

🐝 Boost productivity by coordinating AI agents that learn and adapt, breaking down tasks for efficient, parallel execution.

Kubernetes-Powered Semantic Code Search System

GROQ LPU Powered LLM chat engine

🌐 Centralize AI service management with Claude Code Hub, simplifying API access and enhancing performance for teams and enterprises.

The core source files to this self-hostable successor to the OpenAI Assistants API. To contribute to the core logic, fork or submit pull requests to this repro.

Multi-agent chat runtime for Telegram and QQ/NapCat, built on pi-coding-agent with Docker-isolated agent workspaces.

Dual-agent AI code review loop — consensus at every step, not after the fact. Used to evolve an open-source fork into a production AI assistant with zero manual code.

🎵 Voice-enabled context engineering system for Claude Code with accessibility features and documentation-to-development bridge

Multi-agent software delivery orchestrator that turns GitHub, Linear, and Jira tickets into tested pull requests.

An advanced, local-first agentic CLI coding assistant. Features a multi-agent Tribunal review system and deep semantic indexing for safe, memory-efficient refactoring.

Reusable AI teams for real work: generate, run, and evolve versioned multi-agent teams.

Supporting examples and code for Corti's Agentic Framework.

Multi-agent code factory. GitHub Issues that write their own code. Claude Code + Codex + Gemini with 3 AI reviewers per PR.

Multi-session collaboration for Claude Code: atomic locks, handoffs, memory graph, messaging, hub server, bridge, voice I/O. 166 tests. Zero core deps.

Public documentation for the CapCheck AI fact-checking platform. This repo contains architecture decisions, design patterns, and technical deep-dives without proprietary code.

Build, connect, deploy, and scale true AI agents. 3,000+ pre-built solution templates, 10,000+ integrations, visual canvas, and full code control — everything you need to automate workflows, streamline operations, and supercharge your pipeline on Uplizd.

Coding agent for HPC and scientific-software developers, part of IOWarp's CLIO ecosystem of agentic science.

Auto-activating, multi-agent skill ecosystem for Claude Code, Codex, and Cursor. 51 skills, 26 agents, quality gates, knowledge store, adversarial review, content writing & optimization.

Composable, model-agnostic AI agent skills for multi-agent analysis, verification, research, and multi-model council review. Works with Claude Code, Gemini, Codex, and OpenCode.

tmux for AI Agents — Orchestrate multiple AI coding agents (Codex, Gemini, Claude) in parallel with one command.

This framework maps your entire codebase, tracks how every file change affects everything else, and fixes bugs automatically. Feels like having a senior engineer watching every line you touch.

Your real-life F.R.I.D.A.Y. — a voice-controlled, self-improving AI OS that perceives your screen, remembers everything, writes production code, and gets smarter every week. One founder = one team.

Examples to demonstrate configuration and usage of basic agents and workflows from Microsoft Agent Framework, supporting thread persistence and structured output.

AI Agent Orchestration Platform - Enabling intelligent multi-agent collaboration for development workflows with enterprise-grade reliability and performance

Public-safe Claude Code operating setup with commands, skills, agents, hooks, MCP governance, context-budget discipline, and automated secret/public-safety validation.

An LLM-native cognitive harness for React + Effect TypeScript projects

Command-line ADE tooling to run multiple Claude Code/AI agents in parallel - each in its own isolated git worktree. Spawn, manage, and orchestrate AI-powered development across concurrent tasks without stepping on your own changes.

Google Summer of Code 2025 Project: A comprehensive benchmark for evaluating Large Language Models (LLMs) across the five classic AI agent architectures

An LMS so good you don't have to use it.

【🔥🔥NLP-LLM-Agent🔥🔥】: projects, analysis, source code, model training and testing.

A lightweight starter kit for building and deploying AI agents with Microsoft Foundry Agent Service, featuring Azure integrations, Bicep infrastructure-as-code, and azd deployment for quickly going from prototype to production.

A sophisticated red-teaming agent built with LangGraph and Ollama to probe OpenAI's GPT-OSS-20B model for vulnerabilities and harmful behaviors. (Specifically built for the OpenAI Open Model Hackathon)

Agentic AI Stock Analysis is an AI-powered multi-agent system that analyzes stock market trends, provides analyst recommendations, and fetches the latest news using Groq AI models. It integrates financial and web search agents to deliver real-time insights.

Open-source MCP server for scaffolding MERN stack CRUD resources with Express, Mongoose, React, and preview-safe code generation.

Recursive Claude orchestrator that improves as it builds.

A curated list of awesome AI security tools, frameworks, and resources. OWASP AI Testing Guide, Agentic AI Top 10, EU AI Act, adversarial ML, LLM red-teaming, prompt injection.

Neovim plugin to automatically detect and add agent rules to your CodeCompanion chat context

End-to-end AI-powered video call application where you implement real-time calls with customized AI agents, generate automatic summaries and transcriptions through background processes, and create a post-call experience with video playback, transcript search, and a contextual AI chat. The project also covers authentication, subscriptions, etc

A resilient, fault‑tolerant telemetry analytics pipeline designed to validate, benchmark, and stress‑test high‑frequency sensor data streams under real‑world failure conditions. Includes chaos testing, DLQ repair, GPU‑accelerated ingestion, and end‑to‑end reliability validation for motorsport‑grade telemetry environments.

LLM-powered PR review assistant with OpenAI/Gemini - Analyzes GitHub pull requests and provides structured, actionable code reviews

KubeAgentiX Community Edition

How to build a backup assistant using AI agents on Amazon Bedrock.

Modular skills for AI coding agents.

Unix like `ls` for Google Drive

AI Assistant for FMBench (foundation model benchmarking tool)

🐋 Cloud and AI-native multi-agent orchestration platform for Kubernetes

Explore a curated collection of top AI Agent projects and real-world use cases, including Fellou, Manus, Lovart and more. Discover how AI agents empower automation, data analysis, education, design, and beyond—showcasing the latest in intelligent workflow and creative generation.

Source code of the Arango online documentation

cli for doing awesome claude / codex work

Governed AI-agent workflow platform for authoring, routing, validating, installing, and measuring reusable skills across agents.

Canonical instructions for coding assistants from a single AGENTS.md ✨

FinTS banking CLI for humans and agents. Works great with Claude Code/Cowork, Codex, OpenClaw.

✨ Data-Copilot: 基于函数调用的多智能体协同数据库分析系统 Function-Calling Powered Multi-Agent Database Analytics System✨ 🗣️ 自然语言交互 🤖 多智能体协同，通过函数调用链(Function Call Chain)和函数依赖图谱实现查询/计算/绘图的自动化流水线 📈 智能可视化：自动匹配最佳图表类型，支持交互式图表修改❓ 反问澄清机制：自动识别模糊需求，主动引导用户补充信息 🌐 新加坡数据集成，内置 onemap api 和 HDB房产/学校/地理空间等专项数据库