Python agents

Nebula Nodes — local-first, BYOK node-based AI media canvas for image, video, audio, and 3D workflows, with Claude and Codex agents that build graphs in plain language.

Soul Protocol: An open standard for portable AI identity, memory, and emotion. Like HTTP, but for AI companions.

Open-source, self-hostable runtime for managed AI agents. Apache-2.0.

This repository contains code, resources, and documentation for the workshop "Building a Multi-Agent Workforce with Azure AI Foundry".

A secure runtime for self-correcting AI agents with Docker sandboxing.

Open-source MCP Server for web search, content extraction, library docs & multimodal analysis.

Python LLM-RAG deep agent using LangChain, LangGraph and LangSmith built on Quart web microframework and served using Hypercorn ASGI and WSGI web server.

ITQA (Intelligent Traffic Question-Answering) 是一款专为交通法规咨询与智能出行规划打造的Agentic_RAG 平台。

An AI-powered email assistant that retrieves emails and generates intelligent responses

Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and self-growing tool libraries. Compare 3 sandbox backends: Docker (OpenSandbox), MicroVM, and in-process AST.

🦜🤖 - From natural language to data extraction on Opensearch

LLM-Powered Agents for Object Tracking Databases

Orion - Agente IA local con herramientas Este repositorio contiene el código completo y comentado de un proyecto educativo que muestra cómo construir tu primer agente inteligente con Python y Ollama.

The easiest way to supercharge your apps with LLM!

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 simple Chainlit app for generative question-answering with LangChain and OpenAI.

Finbot is an AI-powered financial chatbot designed to analyse and provide insights on corporate financial performance from 10-K and 10-Q financial documents. This tool leverages langchain and RAG to make complex financial data easily accessible and understandable through a conversational interface.

Code Labyrinth is a tool for using LLM chatbots in coding workflows. It uses Langchain and PGVector to provide context about the working codebase and relevant libraries.

This app allows users to upload CSV or PDF files, or enter text, and ask questions related to the content, no matter how long it is.

The project is a Streamlit-based app that allows users to upload PDF files, processes the text into chunks, stores it in a FAISS vector store using Google Generative AI embeddings, and enables conversational Q&A with the documents using Google Generative AI’s chat model for answers.

LangChain SQL Chatbot lets users query SQLite, PostgreSQL & MySQL with natural language using Streamlit, LangChain & Groq Llama3.

combines web search, Retrieval-Augmented Generation (RAG), reflection, summarization, and follow-up question generation to provide comprehensive answers to user queries

This is a minimal demo project to show the capabilities of a RAG system using LangChain and Milvus, it contains all the things you required to build a basic RAG system.

This repository provides the building blocks for integrating LangChain, LangGraph, and the Tilores entity resolution system.

This experiment will verify different use cases of LLM using LangChain, which include chat, role-playing, and document-based QA.

A RAG implementation on LangChain using Chroma vector db as storage. Take some pdfs, store them in the db, use LLM to inference.

This project provides a Gradio-based web application that allows users to interact with an SQLite database using natural language queries. It leverages the LangChain library and OpenAI's language model to convert plain English questions into SQL queries and execute them on the provided database.

Artificial Intelligence system designed to automate the creation of personalized and detailed travel itineraries based on user interests

An AI powered API for my resume

Backend of cinemattr.ca

The project features two applications: a *Research Assistant* that generates research reports using LangChain, OpenAI's GPT-3.5, DuckDuckGo Search API; and a *Chat With Video* app that allows users to upload videos, transcribe audio with OpenAI's Whisper, and store the embeddings in Pinecone vector DB.

An AI-powered tool by DeepSeek API for summarizing documents, supporting PDFs, DOCX, images, etc. Features OCR for scanned files, bilingual (Chinese/English) output, multiple summary types, smart caching, and real-time progress tracking, with easy setup via Python.

Simple examples of using LLMs and Langchain on Databricks,

This repository is dedicated to my learning journey through the LangChain & Vector Databases in Production course offered by Activeloop. The course is part of the Gen AI 360 Foundational Model Certification and focuses on mastering Large Language Models (LLMs) and Vector Databases.

Develop an advanced chatbot leveraging cutting-edge technologies capable of file uploads, enabling users to receive tailored responses based on the content of the uploaded files. Integrate various tools and agents to enhance the chatbot's capability for comprehensive and accurate responses.

Find what you already know with RAG, Zotero, ChromaDB.

devAI is a Python chatbot for developers. Ask it coding questions or for project help, and it will provide relevant responses. Built with LangChain, it uses natural language processing to understand your queries.

RAG Chatbot for Financial Analysis

A Large Language Model (LLM) Based App to Generate Stories from Pictures

A comprehensive toolkit for building advanced, AI-driven conversational voice agents with a focus on Retrieval-Augmented Generation (RAG). This repository provides a flexible and powerful platform for creating intelligent voice assistants that can interact with users in real-time and provide context-aware responses based on a knowledge base of your

Repo Lens is a powerful tool for seamlessly exploring GitHub repositories. With an integrated AI chatbot that is context-aware and remembers all conversation history, it specializes in answering queries related to the repository's structure, files, and code. This feature makes it easier to understand and navigate codebases.

Short demo on how to use Chainlit library for using Large Language Models API.

This project is a user-friendly web application that allows you to upload PDFs, DOCX files, or images, automatically extracts text using advanced OCR techniques, and generates concise summaries using Google Gemini 2.5 Flash via LangChain. Built with Streamlit, it provides a seamless experience for document understanding and quick insight extraction

PoC using OpenAI API via LangChain to create SPARQL queries that query RDF cubes

User-friendly chatbot that summarizes and interacts with content fromuser-uploaded PDFs using RAG with Ensemble Retriever

This repository contains a Retrieval-Augmented Generation (RAG) pipeline designed to collect, process, and query legal and judiciary data from multiple official sources. The system enables multilingual user interaction and delivers accurate, context-aware responses using an LLM.

A python implementation of Dave Shap's ACE Model

A tool that converts long audio files into a thorough, summarized report. Leverages OpenAI and its API (ChatGPT backend), Langchain for text processing, and Pinecone for vector database facilitation.

HyperFlow is a framework for building agents that rewrite and test their own improvements.

A lightweight framework for building LLM applications, with similar interface as LangChain, but more concise internal implementation.

The "lcel-tutorial" repo is designed for mastering LangChain Expression Language (LCEL), offering exercises to build stateful, multi-actor LLM applications. It's a hands-on guide to leveraging LCEL for complex workflows and agent-like behaviors. Perfect for enthusiasts eager to explore LLM's potential.

The LLM (Large Language Model) in Artificial Intelligence project for our Model T-Shirts Store aims to revolutionize the customer experience by leveraging advanced AI technologies

Simple scripts for GPT-4o Mini using OpenAI API, LangChain and LlamaIndex.

Insight AI: Conduct AI-driven interviews, get real-time summaries, and explore research data via a smart Q&A bot.

Self-hosted search for your private documents. Upload files, find the one you need — or ask and get a cited answer. On your own server, fully offline if you want.

An advanced AI chatbot implementation that combines the power of Groq's LLM with LangChain's tools for internet access, web searching, and conversation memory. This chatbot can search the internet, access Wikipedia, and maintain conversation context while providing informative responses.

This repository contains a project that allows users to analyze PDF files by extracting text from them and performing question-answering tasks

A RAG application to search documents for homeopathic remedies based on patient's description of symptoms and modalities

Customer Support Bot using Langgraph

LLM Chatbot Web UI

Flan-t5 model fine tune LoRA and Langchain

Local chat with your local git based repository, built using Ollama, HuggingFaceEmbeddings, LangChain

LangChain application acting like a Game Master for a table top rpg of your choice.

Backend for Chat with PDF using OpenAI ChatGPT and Hugging Face Lang Chain

LangChain Utilities for prompt generation from documents, URLs, and arbitrary files - streamlining your interactive workflow with LLMs!

📝 Blog Writer Crew AI Agents - Streamlit App 🖋️

AI automatic environment construction and repair, ReAct mechanism

TeamGen AI automates the creation of AI agent teams to address user requests (Developer: Eliran Wong)

Autonomous Agent - Profiling, Memory, Planning, Action, Autogen, MemGPT

Creating Agent Swarm using Open AI, Autogen and Langchain

A CUI-based simple werewolf game with `autogen`

It is an LLM powered assistant (MultiModal RAG) that can read directories, even images, to gather information about companies. You can use HuggingFace or Ollama models,Claude,OpenAI and Google LLMs.I am inspired by IBM Discovery.

Safety challenges for RL and LLM agents' ability to learn and properly apply biologically and economically aligned utility functions. The benchmarks are implemented in a gridworld-based environment. The environments are relatively simple, just as much complexity is added as is necessary to illustrate the relevant safety and performance aspects.

Framework-agnostic AI agent library for building single and multi-agent systems

Claude Code plugin that scaffolds a validated multi-agent ecosystem (orchestrator + N sub-agents + M skills/MCPs) from a natural-language brief. A step up from skill-creator — with semantic validation, trigger-fire evals, and custom MCP scaffolding.

This repository demonstrates how to build a Decoder-Only Transformer with Multi-Query Attention in JAX.

This module implements a post-training mechanism that allows a language model to explore various reasoning branches (chain-of-thoughts) using a Monte Carlo Tree Search (MCTS) framework. It selects the branch with the best answer using a cosine similarity evaluator that compares the candidate answer to a known correct answer.

Multi-agent deliberation system for Claude Code - 3-vendor heterogeneous ensemble (Claude + Gemini + OpenAI)

A Python application that automates the generation of documents using multiple AI agents. Integrates with OpenAI and Anthropic APIs, enabling flexible workflows and customizable outputs for diverse business needs.

AI-powered investment council that summons 18 legendary investors (Buffett, Munger, Soros & more) to analyze any ticker.

Self-hosted social simulation engine. Describe a scene. AI agents with real personalities spawn inside it and start living.

Repository containing the code and explanation of a solution to the Flatland Challenge problem.

Atlaso — desktop app + Python SDK for confidence-flagging AI agent memory. Apache-2.0.

Fabricatio is a Python library designed for building applications that leverage Large Language Models (LLMs) using an event-based agent structure. It utilizes Handlebars for templating and provides a robust framework for managing tasks, workflows, and toolboxes, enabling developers to create intelligent and efficient applications.

Autonomous trading research factory and flagship reference app for Meerkat + Goldfish

A self-evolving, AI-native language and platform for intelligent agents and autonomous software.

"Open-source toolkit (Python Library, Registry API, CLI) for secure, decentralized AI agent interoperability using A2A/MCP."

Lets Threat Model is an AI-driven tool that helps teams identify and manage threats early in the development lifecycle. Built with extensibility and automation in mind, it brings security into agile workflows by generating actionable threat models.

The NL2SQL Agentic Runtime

Teach your LLM to dynamically call your services in Kubernetes

VeoCrafter is an automated video generation pipeline that transforms simple text ideas into engaging short-form videos using Google's VEO-3 AI model.

This repository illustrates the usage of Semantic Kernel in building Agents for Beginners

Middleware for simplifying the design, development, and deployment of agents

An autonomous research and synthesis agent powered by Google Gemini. Features intelligent deep research, query decomposition, and safe local system control via a native Python loop

Agentic Retrieval Augmented Generation App that uses CodeAgents

A multi-agent system specialized for healthcare-related domain

🤖 Enhance AI capabilities with a collection of modular skills for specialized workflows, tool integrations, and domain expertise.

Agentic TRACE is the implementation of the framework described in: https://appliedingenuity.substack.com/p/the-verifiable-orchestrator-a-new

A Model Context Protocol (MCP) server implementation that exposes Pearl's AI and Expert services through a standardized interface

Deploying the schedule-based Serverless Strands Agent on AWS Lambda with CDK, EventBridge and Docker