Python agents

The Eternego codebase

The MathGPT is a web application built with Streamlit that allows users to input mathematical problems and receive solutions. The app supports both text and LaTeX input, making it versatile for various mathematical expressions.

Transactional Memory for AI Agents - Keep SQL and Vector DBs in sync with ACID-like guarantees

Runtime detector for reward hacking and misalignment in LLM agents (89.7% F1 on 5,391 trajectories).

A lightweight AI agent which reads and summarizes research papers for you.

AI-Enhanced Teaching Assistant: Bridging Instructor Knowledge and Web Intelligence

A collection of Dagger modules I built and published

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。

The Customer Care Bot is a cutting-edge customer support solution designed to revolutionize the way e-commerce websites interact with and assist their customers. Powered by OpenAI's advanced GPT-3.5 language model, this intelligent bot offers a seamless and personalized customer service experience.

AI Studio by Metric Coders: A No-Code Software to train, download and deploy Large Language Models.

Webapp to answer questions about my resume leveraging Langchain, OpenAI, Streamlit

Python web app built on Streamlit, utilizing LangChain and the OpenAI API to automate YouTube title and script generation. The app offers a prompt-based interaction system, leveraging conversational memory and Wikipedia research. Resulting in a streamlined user interface to showcase outputs, history, and related Wikipedia research.

Template for an AI application that extracts the job information from a job description using openAI functions and langchain

Private semantic search for your Obsidian vault

A command-line tool for developers to get instant code reviews from state-of-the-art Large Language Models (LLMs). Supports both local models (Ollama) and cloud providers (OpenAI, Hugging Face, Azure). Improve code quality, catch bugs, and receive AI-driven feedback effortlessly.

Learning and building LLM application using Langchain 🦜🔗 and Open AI

Example of running LangChain on Digitalocean App Platform

The personal assistance chatbot integrates appointment creation, Google Calendar event scheduling with Google Meet, and email notifications using the Langchain and Zapier NLA integration.

Your personalized museum tour guide!

🦜️🔗 LangChain中文网: 500页超详细中文文档教程，助力LLM/chatGPT应用开发

Customized bot with langchain and gpt4

A web-based application enabling users to interact with and extract insights from YouTube video transcripts and website content. This solution aims to enhance user engagement, streamline content exploration, and provide actionable insights efficiently.

The Universal Agent Interoperability Protocol: The TCP/IP of the AI Economy

Build LLM-enabled FastAPI applications without build configuration.

Ask anything to PDFs.

Intro workshop to Amazon Bedrock

A powerful app that uses AI to provide human-readable explanations for your terminal errors.

Ollama RAG using SQL Database

LangReact 是一个配置化的 Planning Agent 应用开发工具，通过配置、插件，能快速为你的 GPT 应用提供 Planning 功能。

AIChainComposer is a tool to quickly and easily compose complex LLM chains. A sophisticated wrapper around core LangChain functionality, AIChainComposer allows for the generation of complex multi-layer LLM chains without ever touching any LangChain code.

It is a chatbot based on LangChain.

AI小说创作系统 - 基于多Agent协作的智能小说创作平台，支持世界观管理、角色管理、大纲管理和一致性保障

Stop writing Terraform by hand. A multi-agent framework that researches, generates, validates, and commits production-ready AWS infrastructure modules through conversation.

NeuralCache is a drop-in reranker for Retrieval-Augmented Generation (RAG) that learns which context the model actually uses.

Multi-agent RAG system using AutoGen for document-focused tasks in medical education, leveraging LangChain, ChromaDB, and OpenAI embeddings.

This project has implemented the RAG function on Jetson and supports TXT and PDF document formats. It uses MLC for 4-bit quantization of the Llama2-7b model, utilizes ChromaDB as the vector database, and connects these features with Llama_Index. I hope you like this project.

a QA bot on contents of given docs 用所给文档进行问答的聊天机器人

Open AI APIs with Llama Index and Milvus Vector DB for Retrieval Augmented Generation (RAG) testing

[IROS'25] COCMT

It shows an intelligent agent based on LangGraph for long form writing.

Mandali (मंडली) — Autonomous multi-agent adversarial collaborative system using GitHub Copilot SDK

SmartAgentic is a project-centric, multi-agent memory OS for software engineering. It turns conversations and code decisions into an evolving knowledge graph so teams keep context across sessions, reduce contradictions, and ship.

The simplest way to deploy, manage, and scale AI agents in your Kubernetes cluster with declarative YAML configurations

Your site's built-in, self-hosted AI web dev. Chat to build, update, and manage your entire website. The CMS, reimagined.

TrustifAI: A Comprehensive Framework for AI Trustworthiness

An agentic solution designed to create a llms.txt file for any given repo or folder.

AI-powered developer onboarding platform using natural language to deploy applications via GitOps. Golden path workflows with ArgoCD and OpenRouter integration.

A framework to orchestrate multiple AI agents, enabling them to collaborate efficiently through smart threading, dependency management, context sharing, and distributed execution via a built-in swarm system. Built on top of smolagents, it allows the creation of an AI dream team that can scale to tackle complex tasks.

Open-source security gateway for MCP agents and tools. Inspect tool calls before execution, enforce policy, block risky operations, and emit audit-ready evidence.

Validation and permission system for Claude Code

MCP server empowering AI assistants with real-world capabilities: Gmail, Calendar, Tasks, Git integration, and note management. Bridges AI assistants to external services through standardized protocol with secure authentication.

A self-hosted job alert bot for jobs that are actually remote (not just US-remote)

Ask questions about your business data in plain English, Get automatic SQL queries and visualizations, Receive AI-powered insights and recommendations, No SQL knowledge required

A travel agent python app built with LangGraph using GPT model from OpenAI to be run locally or on CI/CD with Github Actions

Multi-agents operating system layer on top of Claude Code

Local-first LLM wiki for research workflows with Obsidian, a dashboard, and a macOS menubar runtime.

Dual-mode AI assistant (CLI + Telegram) powered by Perplexity AI. Fast, modular, and cross-platform.

A powerful, multi-modal Telegram bot leveraging cutting-edge AI technologies including Gemini, DeepSeek, OpenRouter, and 50+ AI models for comprehensive conversational assistance, media processing, and collaborative features with MCP (Model Context Protocol) integration.

Apache Flink MCP Server is a Model Context Protocol (MCP) implementation that empowers AI assistants and large language models to interact directly with Apache Flink clusters through natural language. It enables intelligent monitoring, management, and analysis of real-time streaming applications—making stream processing more intuitive, accessible.

Welcome to the Document QA system! This repository contains the code for a system that allows you to ask questions about your documents and get answers based on their contents. It supports a wide range of document formats, including PDF, Word, Excel, PowerPoint, text files, and even images!

Intentional is an open-source framework to build reliable LLM chatbots that actually talk and behave as you expect.

For facebook comment and messenger fan page.

Streamlit Multi AI platform Claude Chat APP

PallmaAI delivers complete, lifecycle security for your AI agents, from proactive red teaming to real-time threat detection and automated remediation.

A Telegram bot that allows you to create your own ChatGPT in Telegram.

Autonomous, personalized research loops for Claude Code. Set a topic, walk away, come back to a quality-gated report adapted to your projects.

This project demonstrates how to integrate a “think” tool into a LangGraph agent workflow, inspired by Anthropic’s research on structured reasoning in tool-based agents. By leveraging the “think” tool, Claude is enabled to pause and reflect on intermediate steps, improving performance in complex, policy-driven, or multi-step decision scenarios.

Browse, search and download AI agent skills

Perform intelligent research over document collections using hybrid search and LLMs.

In-memory vector database with pluggable indexing algorithms, metadata filtering, and a FastAPI-based REST API.

Official implementation of "RAViG-Bench: A Benchmark for Retrieval-Augmented Visually-rich Generation with Multi-modal Automated Evaluation"

This project is an end-to-end Retrieval-Augmented Generation (RAG) system designed to ingest, parse, embed, and semantically search scientific papers from arXiv.

Exploring the use case of LLMs in healthcare, in particular assisting in document retrieval and summarization.

This is an LLM agent for college students to study courses by themselves. Upload your textbook and enjoy the learning experience now!

AI Search Engine in 70 lines

Convert any image into a Region Adjacency Graph (RAG)

This project is an automated research and summarization tool that allows users to conduct research on a specific question and summarize the information found and present it as a blog post.

Artificial Intelligence

SpeakingAI is a demo of privately deployable 'GPT-4o like AI + RAG', a fully functional web AI server with audio query/answer in streaming, using LLM and RAG for backend knowledge.

Web application for benchmarking and comparing LLM behaviour, energy and emissions on cloud and bare metal under different inference configs, middleware scaffolds and post-training implementations

An interactive Streamlit dashboard for visualizing TSLA OHLCV data with TradingView Lightweight Charts, enriched with trade markers, support/resistance bands, and an AI chatbot powered by Gemini.

For unmanned missions into GPT returning structured data

🦀 The first autonomous hackathon agent stop assisting and start competing (🏆 Hackathon Champion Project).

Your Desktop, From Anywhere. AI-powered remote desktop control from your phone.

A comprehensive Model Context Protocol (MCP) server providing real-time YouTube Data API access for AI assistants. Features 14 functions including intelligent content evaluation with technology freshness scoring for knowledge base curation.

Semantic code search for AI agents — 166+ languages, hybrid search, works offline

This is an official repository for "Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery".

AgentForensics is an open-source security framework that monitors complete LLM agent sessions in real time, detecting prompt injection attacks across tool outputs, web pages, documents, and API responses. It uses heuristic rules, a DistilBERT ML classifier, instruction boundary detection, semantic drift, and sliding-window multi-turn detection.

Elevate your health journey with our Diet & Workout Recommendation System on Google Gemini Pro! Personalized suggestions based on age, sex, height, weight, region, dietary preferences, allergies, and health conditions. Optimize your well-being effortlessly!

This project automates posting tweets on Twitter about AI news articles. The bot scrapes AI news articles, generates tweets, creates related images, and posts the tweets. The process is repeated periodically to ensure the latest AI news is posted.

Contract-driven architecture for building LangGraph agents with declarative node definitions, automatic graph construction, and hybrid rule/LLM-based routing.

A FastAPI-based Retrieval-Augmented Generation (RAG) system for legal document analysis, powered by Pinecone, LangChain, and Llama 3.3

Entirely Local AI Voice Assistant - Created using LangChain, Ollama, Whisper, Speech Recognition, and Sapi5

In this end to end project I have built a RAG app using ObjectBox Vector Databse and LangChain. With Objectbox you can do OnDevice AI, without the data ever needing to leave the device.

AI-powered CLI tool to identify and automatically unsubscribe from marketing emails in Gmail using LLMs (Gemini, Claude, OpenAI) and browser automation

YouTube Video Inspector is a multi-agent tool that analyzes YouTube videos by fetching metadata, analyzing comments, and generating performance reports, which can be exported as PDFs using CrewAI.

Local RAG system with a built-in governance agent that filters sensitive or restricted information with separated agent logging systems to keep privacy and security

A multi-agent system built with DSPy that coordinates research and writing agents to produce comprehensive articles on any topic.

多智能体科研助手：文献搜索、知识图谱、TRL评估、创新假设生成

Autonomous Software Engineering Agents — self-healing, self-diagnosing development team powered by Claude Code and A2A protocol