Awesome GitHub RepositoriesStateless Execution

Deepagents is an LLM agent orchestration platform and stateful application server designed for deploying and managing AI agents built with computational graphs. It provides a containerized runtime environment that handles agent execution, state persistence, and the versioning of AI assistants. The platform distinguishes itself through deep integration with the Model Context Protocol, allowing agents to function as servers that expose tools and capabilities to external clients. It features a sophisticated observability suite for capturing execution traces, performing LLM-based evaluations agai

LangChain.js is a framework for building, executing, and monitoring stateful agentic applications. It provides an orchestration engine that models workflows as directed graphs, allowing developers to connect language models, data sources, and external tools into modular, multi-step processes. The platform distinguishes itself through its focus on stateful execution and human-in-the-loop control. It manages agent lifecycles by persisting execution state across threads, enabling fault tolerance and the ability to pause workflows at designated breakpoints for manual review or modification. This

Laf is a serverless backend platform that provides an integrated environment for cloud functions, a document database, and file storage. It serves as a complete infrastructure for developing and deploying backend logic, data persistence, and real-time communication without the need for manual server management. The platform features a browser-based IDE that allows developers to write, test, and deploy serverless functions directly within a web editor, removing the requirement for local environment setup. It also includes a WebSocket communication platform for maintaining persistent bidirectio

geckodriver es un controlador de automatización de navegador y una implementación de W3C WebDriver. Funciona como un servidor proxy que traduce comandos de WebDriver estandarizados en instrucciones internas para navegadores web basados en el motor Gecko. El proyecto permite el control programático de navegadores basados en Gecko para simular interacciones de usuario y automatizar tareas web repetitivas. Admite tanto la automatización de navegador estándar como la orquestación de navegadores headless para flujos de trabajo que se ejecutan sin una interfaz gráfica de usuario. El software se utiliza para pruebas web automatizadas para verificar la funcionalidad del sitio web y el comportamiento de la interfaz de usuario ejecutando suites de pruebas programáticas contra un navegador en vivo.

OpenWhisk is a serverless cloud platform designed for deploying and executing stateless functions in response to API calls or events. It serves as a complete serverless stack, providing an API gateway for functions, a function-as-a-service runtime manager, and an event-driven workflow engine. The platform distinguishes itself through a polyglot execution model that supports multiple language runtimes and allows for the creation of custom runtimes using Docker containers. It enables complex logic through function orchestration and composition, allowing multiple functions to be chained into seq

Keyhacks is a command-line tool that tests whether API keys and tokens for dozens of cloud services are valid and active. It automates the verification of discovered credentials during security auditing and penetration testing, confirming if leaked or harvested API keys, tokens, and secrets are still operational. The tool validates credentials by sending lightweight, service-specific HTTP requests to each platform's API endpoint and inspecting the response status or body. Each validation runs independently without storing state between requests, using pre-defined request templates with the co

Ottomator-agents is a framework for building and deploying autonomous AI agents using structured workflow files and source code. It serves as a declarative deployment tool and workflow orchestrator that translates static configuration files into executable sequences of AI agent tasks and logic flows. The system utilizes manifest-driven instantiation and template-driven deployment to create functional agent identities by populating source code templates with user-specified parameters. It incorporates a modular skill system that equips agents with discrete, reusable source code units and toolse

Este proyecto es un repositorio de implementación de algoritmos y una guía de práctica para entrevistas de codificación. Proporciona una colección de soluciones algorítmicas, referencias de estructuras de datos y materiales de estudio diseñados para preparar a los candidatos para evaluaciones de contratación en ingeniería de software. El repositorio funciona como una suite de pruebas de algoritmos, utilizando un sistema de verificación basado en casos que ejecuta pares específicos de entrada-salida para validar la corrección de la lógica implementada. El código base cubre la preparación técnica para entrevistas mediante la práctica de problemas comunes de ciencias de la computación, la implementación de estructuras de datos centrales y la verificación de soluciones de codificación.

This project is a collection of practical and idiomatic Python code recipes, technical tutorials, and programming references. It serves as an example-driven resource that translates theoretical programming concepts into executable Python source code. The repository is organized as a series of standalone scripts and modular recipes. Each sample is designed for stateless execution, allowing individual problem-solving patterns to be run independently without shared global state or complex setup. The content focuses on Python language mastery and software development. It covers the implementatio

This project provides a translation layer and set of adapters designed to bridge AI agents with the Model Context Protocol. It functions as an integration layer that allows agents to operate as protocol-compliant servers and enables the conversion of protocol-based tools into formats compatible with agent frameworks and logic graphs. The adapters facilitate tool interoperability by wrapping external protocol tools for use within agent workflows and exposing internal agent capabilities to any client implementing the Model Context Protocol. This creates a communication bridge that supports inte

OSINT-SPY es un framework de reconocimiento de código abierto diseñado para recopilar inteligencia sobre infraestructura digital y rastrear actividad financiera a través de libros contables distribuidos. Funciona como un orquestador centralizado que consulta múltiples servicios de terceros y bases de datos públicas para agregar puntos de datos de seguridad en un formato unificado. El sistema utiliza una arquitectura modular basada en plugins que permite tareas de recopilación de datos independientes, que van desde el reconocimiento de dominios y direcciones IP hasta el análisis de archivos remotos en busca de firmas maliciosas. Admite investigaciones especializadas en transacciones de criptomonedas, permitiendo a los usuarios monitorear el movimiento de activos digitales y recuperar datos históricos de blockchain. Más allá del reconocimiento, la herramienta incluye utilidades para auditar la postura de seguridad de la infraestructura web pública, como identificar cifrados de encriptación admitidos y detectar vulnerabilidades comunes. El software opera bajo un modelo de ejecución sin estado, asegurando que cada escaneo permanezca como un proceso aislado sin persistir estado entre sesiones.