Awesome GitHub RepositoriesDurable Execution Persistence

Conductor is a durable workflow engine designed to orchestrate complex, long-running business processes and autonomous agent loops. It functions as a stateful execution platform that persists the entire history of a process, ensuring that workflows remain reliable and recoverable across infrastructure failures, system restarts, and transient network errors. By managing task lifecycles, worker polling, and state transitions, it provides a centralized coordination layer for distributed systems. The platform distinguishes itself through its specialized support for AI agent orchestration, allowin

Conductor is a distributed workflow manager and microservices orchestration engine. It coordinates long-running business processes across a network of services, using a stateful orchestration model to ensure consistent execution order and reliable state management. The system defines task sequences and conditional business logic using structured JSON configuration files. It manages the execution of complex operations across distributed systems with built-in persistence and failure recovery, tracking the progress of processes through a backend database. The platform provides capabilities for

Cadence is a distributed workflow orchestration engine designed to execute long-running, asynchronous business logic with built-in durability and resilience across distributed systems. It functions as a stateful process manager that ensures processes resume from their last known state following system crashes or network outages. The platform utilizes a distributed task queue to manage work across independent worker nodes and supports persistence via SQL or Cassandra backend storage. It includes a workflow visualization dashboard for inspecting execution histories and state traces, alongside a

This project is a comprehensive framework for the orchestration, evaluation, and context management of large language model agents. It provides a set of architectural patterns and standards for designing agent interactions, integrating external tools, and establishing memory architectures to persist knowledge across sessions. The system focuses on optimizing the limited memory of language models through token-aware context compression and filesystem-based context offloading. It incorporates secure execution environments using sandboxed virtual machines and isolated containers to safely run ba

Flyte is a distributed machine learning pipeline manager and MLOps workflow engine. It functions as a Kubernetes-native orchestrator used to coordinate data, models, and compute resources for executing machine learning pipelines and autonomous agents at scale. The platform provides specialized infrastructure for the full machine learning lifecycle, including a dedicated model serving platform to deploy trained models as scalable production-ready inference services. It also enables the coordination and state management of autonomous AI agents. The system manages scalable pipeline execution th

Inngest is a durable execution framework and event-driven automation engine designed to orchestrate background workflows. It enables developers to build resilient, stateful processes by memoizing function steps, ensuring that long-running tasks can automatically resume from the last successful operation after failures, timeouts, or infrastructure restarts. The platform distinguishes itself through its event-driven architecture, which uses a schema-validated bus to trigger functions and coordinate complex, multi-step logic. It employs an onion-model middleware approach for cross-cutting concer

Open Canvas es un sistema para gestionar flujos de trabajo de agentes de IA con estado a través de un editor colaborativo y un framework de orquestación. Proporciona un espacio de trabajo compartido donde humanos y modelos de lenguaje de gran tamaño co-escriben documentos y escriben código en tiempo real, respaldado por un editor de texto estructurado con renderizado en vivo. El proyecto destaca por integrar un gestor de estado que rastrea el contexto de la sesión, memorias de usuario e instantáneas históricas a través de hilos de conversación. Emplea un modelo de ejecución duradero que permite intervenciones humanas (human-in-the-loop) y mantiene un sistema de seguimiento de versiones para documentos y bloques de código. El framework cubre una amplia superficie de capacidades, incluyendo interfaces de modelos agnósticas al proveedor para chat y embeddings, composición de flujos de trabajo impulsada por middleware para guardrails y enrutamiento, y gestión de contexto personal para almacenar preferencias de usuario. Incluye además herramientas para la depuración de ejecución de agentes y la capacidad de desplegar el servidor mediante imágenes de contenedor. Se proporciona un servidor de agente local para manejar ejecuciones, hilos y almacenamiento persistente.

ZenML is an extensible machine learning orchestration framework designed to manage the end-to-end lifecycle of data pipelines and AI agent workflows. It functions as a durable orchestrator that executes machine learning tasks as directed acyclic graphs, ensuring that every step is containerized for consistent performance across local, cloud, and hybrid infrastructure. By decoupling pipeline code from underlying compute and storage backends, the platform allows developers to define infrastructure-agnostic stacks that remain portable across diverse environments. The project distinguishes itself

ZenML is an orchestration platform designed for building, deploying, and monitoring reproducible machine learning pipelines and agentic workflows. It provides a unified framework that manages the entire lifecycle of machine learning assets, from data processing and model training to the deployment of persistent inference services. By decoupling pipeline logic from underlying compute and storage, the platform enables teams to transition workflows seamlessly from local development environments to production-grade cloud infrastructure. The platform distinguishes itself through a service-oriented

OpenSquilla es un framework de orquestación de agentes LLM diseñado para coordinar flujos de trabajo de IA de varios pasos y la ejecución de herramientas mediante grafos acíclicos dirigidos. Funciona como un sistema centralizado para gestionar paquetes de habilidades especializadas y ejecutar secuencias de razonamiento complejas. El proyecto se distingue por una pasarela de enrutamiento que dirige las tareas a diferentes proveedores de IA según la complejidad, el coste y el rendimiento. Utiliza un sistema de memoria de IA de varios niveles que organiza el conocimiento de trabajo, episódico y semántico mediante embeddings locales y SQLite, junto con un sandbox de ejecución seguro que aísla el código generado por el agente mediante perfiles de permisos basados en riesgos. La plataforma cubre una amplia gama de capacidades, incluyendo despliegue multicanal en web y plataformas de mensajería, programación automatizada de tareas mediante cron y un puente de Model Context Protocol para conectar con herramientas externas. También proporciona herramientas integrales de monitoreo y observabilidad para rastrear costes de tokens, auditar decisiones en tiempo de ejecución y gestionar un catálogo de habilidades reutilizables. El sistema incluye utilidades de línea de comandos para la inicialización del espacio de trabajo y la gestión del ciclo de vida de las habilidades.

Workflow is a platform for executing long-running, stateful processes that automatically persist progress and recover state after system interruptions. It functions as a durable orchestration engine designed to manage complex, multi-step asynchronous operations within distributed systems. The framework distinguishes itself through event-sourcing and checkpointing mechanisms that record execution steps as an immutable log, allowing for precise state reconstruction after failures. It provides sandboxed task isolation to run side-effect-heavy logic in restricted environments, ensuring that sensi