Python agents

Command-line interface for performing software engineering tasks using large language models. It is based on Cline, but is simpler, uses fewer input tokens, has fewer capabilities, and does not depend on VSCode.

A lightweight, extensible cybersecurity toolkit that connects AI assistants to security tools through the Model Context Protocol (MCP), enabling AI-assisted security research, scanning, and analysis.

Agentic AI Software Engineer that can convert natural language to executable code

It automatically describes images in PDF files and generates questions from these descriptions. With its advanced RAG structure, it directs these questions directly to PDF text content, providing comprehensive information extraction and analysis.

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).

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

Chat with your PDFs using AI! This Streamlit app uses RAG, LangChain, FAISS, and OpenAI to let you ask questions and get answers with page and file references.

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

Stop being locked into one LLM provider. UnifyRoute is a self-hosted gateway that routes, fails over, and manages quotas across OpenAI, Anthropic, and more with a drop-in OpenAI-compatible API.

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

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.

一个基于自定义知识库的实用型电子产品AI问答与推荐系统，使用Python FastAPI后端和Vue.js前端。

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.

Validation and permission system for Claude Code

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

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.

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.

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.

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"

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

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

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

The 3rd Eye is a modular OSINT (Open Source Intelligence) framework built on an agent-based, graph-driven architecture. It automates public information discovery, identity correlation, and exposure analysis across multiple platforms, and generates structured intelligence reports. The system follows a LangGraph agent design.

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.

Production-ready Chainlit RAG application with Pinecone pipeline offering all Groq and OpenAI Models, to chat with your documents.

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.

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

Query latest medicinal suggestions and your basic queries in interactive way.

RLM-powered CV tailoring for job applications.

A simple ReAct agent that has access to LlamaIndex docs and to the internet to provide you with insights on LlamaIndex itself.

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.

Seamlessly integrate IoT data with AI agents, enabling the effortless parsing, processing, and utilization of IoT data streams.

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

Cookiecutter template for MCP server development with FastMCP

umbra is an open-source project exploring digital personhood. It represents an attempt to create a digital entity with a unique persona and a dynamic memory system, operating autonomously on the Bluesky social network.

ToolOps is a framework-agnostic middleware SDK that treats every tool call as a first-class operation. By wrapping your tools in a single decorator, you instantly upgrade them with industrial-grade caching, resilience, and observability.

ExcelFlow: AI-powered Excel assistant with natural language processing. Chat with your spreadsheets using OpenAI GPT-4o, perform operations, and get insights through a modern React + FastAPI web interface. Real-time updates via WebSockets.

小遥配配，AI 对话式电脑导购，帮你 24 小时接单。Xiaoyaopeipei, AI-Powered PC Shopping Assistant. Taking Orders 24/7 for You.

Persistent memory for AI coding agents via MCP — a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter + Gemini Flash → Neo4j (via Graphiti). 12 MCP tools, hierarchical clusters, two-regime confidence decay.

Memory architectures that evolve with your agent