awesome-repositories.com
Blog
MCP
awesome-repositories.com

Entdecke die besten Open-Source-Repositories mit KI-gestützter Suche.

EntdeckenKuratierte SuchenOpen-Source-AlternativenSelf-hosted SoftwareBlogSitemap
ProjektMCP-ServerÜber unsRanking-MethodikPresse
RechtlichesDatenschutzAGB
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

16 Repos

Awesome GitHub RepositoriesMulti-Step Workflow Orchestration

Chains together multiple actions and conditional logic into reusable workflows for complex automation tasks.

Distinct from Automated Workflow Orchestration: Distinct from Automated Workflow Orchestration: focuses on multi-step orchestration with conditional branching, not just chaining.

Explore 16 awesome GitHub repositories matching devops & infrastructure · Multi-Step Workflow Orchestration. Refine with filters or upvote what's useful.

Awesome Multi-Step Workflow Orchestration GitHub Repositories

Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
  • tektoncd/pipelineAvatar von tektoncd

    tektoncd/pipeline

    8,996Auf GitHub ansehen↗

    Pipeline ist ein Kubernetes-natives CI/CD-Framework und ein Cloud-nativer Pipeline-Orchestrator. Es fungiert als Custom Resource Controller, der deklarative Pipeline-Definitionen in koordinierte Pod-Ausführungen und verwaltete Workloads übersetzt. Das System agiert als containerisierter Task-Runner, der die Ausführung eigenständiger Build-Schritte und wiederverwendbarer Aufgaben ermöglicht, die spezifische Eingaben verarbeiten, um definierte Ausgaben zu erzeugen. Es erlaubt die Orchestrierung komplexer Workflows durch die Ausführung einer Sequenz unabhängiger Container als modulare Komponenten innerhalb einer Cloud-Umgebung. Die Plattform deckt die automatisierte Softwarebereitstellung und die Orchestrierung containerisierter Aufgaben ab und unterstützt eine Multi-Tenant-Build-Infrastruktur durch Ressourcenisolierung. Sie bietet Funktionen zur Überwachung von Ausführungsprotokollen und Fortschritt sowie die Erstellung wiederverwendbarer Pipeline-Komponenten, die über verschiedene Namespaces und Projekte hinweg geteilt werden können.

    Creates reusable sequences of steps that execute build or delivery tools using specific inputs and outputs.

    Go
    Auf GitHub ansehen↗8,996
  • julep-ai/julepAvatar von julep-ai

    julep-ai/julep

    6,607Auf GitHub ansehen↗

    Julep ist eine Plattform zur Orchestrierung von LLM-Agenten und ein Multi-Tenant-KI-Backend, das für den Bau autonomer Agenten mit persistentem Gedächtnis, Tool-Integration und komplexen, mehrstufigen Workflows entwickelt wurde. Es dient als Framework zur Konfiguration von Agenten-Identitäten und Verhaltenseinstellungen, um spezialisierte berufliche Rollen zu automatisieren. Die Plattform zeichnet sich durch ihr zustandsbehaftetes Sitzungsmanagement und ihre RAG-Infrastruktur-Engine aus, die es Agenten ermöglichen, eine langfristige Interaktionshistorie zu pflegen und Antworten auf indizierten privaten Dokumenten zu fundieren. Sie bietet Infrastrukturfunktionen auf Enterprise-Niveau, einschließlich eines sicheren Vaults für verschlüsselte Secret-Speicherung und Token-basierter Isolierung, um den Datenschutz zwischen verschiedenen Benutzerkonten zu gewährleisten. Das System deckt ein breites Spektrum an Funktionen ab, einschließlich Workflow-Orchestrierung mit bedingter Logik, Echtzeit-Überwachung der Ausführung und Middleware für die Nachverfolgung von Ressourcenkosten. Es enthält zudem Tools zur Integration privater APIs und Drittanbieterdienste sowie eine Command Line Interface zur Verwaltung von Agenten-Lebenszyklen. Die Management-Plattform kann auf selbst gehosteter Infrastruktur bereitgestellt werden, um die Kontrolle über Daten und Dienstverfügbarkeit zu behalten.

    Sequences prompts and tool calls using conditional logic and parallel execution to automate complex processes.

    Jupyter Notebook
    Auf GitHub ansehen↗6,607
  • stackstorm/st2Avatar von StackStorm

    StackStorm/st2

    6,487Auf GitHub ansehen↗

    StackStorm is an event-driven automation platform that watches for events from external systems and triggers workflows, actions, and remediation across infrastructure tools. At its core, it provides a workflow orchestration engine that chains multiple actions and conditional logic into reusable, multi-step workflows for complex automation tasks, alongside a rules engine that applies matching criteria to triggers and maps trigger payload data to action inputs for automated responses. The platform distinguishes itself through a ChatOps integration framework that enables executing commands and r

    Chains together multiple actions and conditional logic into reusable workflows for complex automation tasks.

    Pythonauto-remediationautomationchatops
    Auf GitHub ansehen↗6,487
  • j3ssie/osmedeusAvatar von j3ssie

    j3ssie/Osmedeus

    6,425Auf GitHub ansehen↗

    Osmedeus is a security workflow orchestration engine that coordinates AI agents, shell commands, and scanning tools through declarative YAML pipelines. It functions as a distributed security scanner, a declarative workflow automator, and an AI agent framework for security, enabling automated multi-step security analysis with conditional branching, parallel execution, and distributed workers. The engine distinguishes itself through a hybrid runner model that executes workflow steps on the local host, inside Docker containers, or over SSH to remote machines, selected per step or module. It supp

    Evaluates JavaScript utility functions as workflow steps, conditions, and decision points for scanning logic.

    Go
    Auf GitHub ansehen↗6,425
  • chaosblade-io/chaosbladeAvatar von chaosblade-io

    chaosblade-io/chaosblade

    6,355Auf GitHub ansehen↗

    ChaosBlade is an open-source chaos engineering platform that injects faults into applications, containers, Kubernetes clusters, and host systems to test resilience. It functions as a multi-layer fault injection tool, capable of disrupting system resources, Java, C++, NodeJS, and Golang applications, Docker containers, and Kubernetes pods and nodes from a single interface. The platform distinguishes itself through its architecture, which defines chaos experiments as Kubernetes Custom Resource Definitions for native cluster integration, and supports multiple fault injection mechanisms including

    Runs faults in sequence or parallel phases where multiple faults activate and recover together.

    Pythonalibabachaos-engineeringchaos-testing
    Auf GitHub ansehen↗6,355
  • appleboy/ssh-actionAvatar von appleboy

    appleboy/ssh-action

    6,113Auf GitHub ansehen↗

    This is a GitHub Action that executes shell commands on remote servers over SSH as part of a CI/CD pipeline. It supports authentication using passwords, private keys, or private keys with passphrases, and can verify the SHA256 fingerprint of the remote host's public key before connecting to prevent man-in-the-middle attacks. The action can connect to multiple remote hosts in a single workflow step, optionally executing commands synchronously across all of them. It also supports routing SSH connections through an intermediate jump host to reach target servers in restricted networks. Environmen

    Executes commands across multiple remote hosts simultaneously from a single workflow step.

    Shell
    Auf GitHub ansehen↗6,113
  • grapeot/devin.cursorrulesAvatar von grapeot

    grapeot/devin.cursorrules

    5,970Auf GitHub ansehen↗

    Devin.cursorrules is a configuration framework that transforms Cursor and Windsurf IDEs into autonomous coding agents capable of executing multi-step development workflows without manual step-by-step prompting. It provides a structured set of rule files and configuration templates that extend native IDE agent functionality with automated planning and extended tool capabilities. The project bootstraps an agentic coding environment through a cookiecutter template or direct file copy, injecting plain-text configuration files into the project root that define agent behavior and tool integrations.

    Orchestrate complex workflows like data gathering, prototyping, and cross-referencing external resources without requiring manual step-by-step prompting.

    Python
    Auf GitHub ansehen↗5,970
  • fizzadar/pyinfraAvatar von Fizzadar

    Fizzadar/pyinfra

    5,793Auf GitHub ansehen↗

    pyinfra is an agentless infrastructure automation framework that turns declarative Python code into idempotent shell commands to manage servers, containers, and local machines over SSH without requiring any pre-installed software on target hosts. It operates by comparing the desired state of a system against its current state, using a dry-run simulation mode to preview changes and a fact-based conditional execution engine to gather host attributes at runtime and control which operations run. The tool compiles Python operations into optimized shell commands and executes them in parallel across

    Scales operations from one server to thousands of hosts simultaneously via SSH orchestration.

    Python
    Auf GitHub ansehen↗5,793
  • andrewyng/translation-agentAvatar von andrewyng

    andrewyng/translation-agent

    5,765Auf GitHub ansehen↗

    Translation Agent is a Python-based system that uses a large language model to translate text through a multi-step agentic workflow. Rather than producing a single output, it generates an initial translation, then prompts the same LLM to critique its own work and produce improvement suggestions, and finally refines the translation based on that self-critique. This reflection-driven iterative refinement loop is the core mechanism for improving translation quality without requiring human feedback or additional training data. The system distinguishes itself through two key capabilities. First, i

    Coordinates a lightweight Python script that sequences stateless LLM calls without a dedicated runtime.

    Python
    Auf GitHub ansehen↗5,765
  • aws-samples/aws-cdk-examplesAvatar von aws-samples

    aws-samples/aws-cdk-examples

    5,605Auf GitHub ansehen↗

    Dieses Projekt ist eine Referenzbibliothek und eine Sammlung von Beispiel-Code-Mustern für die Bereitstellung von Cloud-Infrastruktur mithilfe des AWS CDK. Es bietet eine Reihe von Beispielprojekten, die demonstrieren, wie Rechen-, Speicher- und Netzwerkressourcen mithilfe allgemeiner Programmiersprachen definiert werden. Die Bibliothek enthält Referenzimplementierungen für verschiedene Architekturmuster, einschließlich serverloser Backends mit GraphQL- und WebSocket-APIs, Container-Orchestrierung mit Load Balancern und Auto-Scaling sowie globales Hosting statischer Websites via Content Delivery Networks. Sie bietet zudem Entwürfe für isolierte Netzwerktopologien und ereignisgesteuerte Workflow-Automatisierung mithilfe von Zustandsmaschinen. Die abgedeckten Funktionen erstrecken sich auf die Verwaltung relationaler Datenbanken, die Konfiguration sicherer Dateiübertragungsserver und die Implementierung fein abgestufter Autorisierung. Zusätzlich demonstrieren die Beispiele Techniken zur Infrastrukturanpassung, wie das Überschreiben von Ressourceneigenschaften und die Integration benutzerdefinierter Ressourcen.

    Implements multi-step state machine workflows to coordinate distributed serverless components.

    Pythoncdkcdk-examples
    Auf GitHub ansehen↗5,605
  • inngest/inngestAvatar von inngest

    inngest/inngest

    5,499Auf GitHub ansehen↗

    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

    Chains discrete, retriable steps into complex workflows that maintain state across execution boundaries.

    Go
    Auf GitHub ansehen↗5,499
  • maiot-io/zenmlAvatar von maiot-io

    maiot-io/zenml

    5,452Auf GitHub ansehen↗

    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

    Encapsulates logic into modular, reusable units that accept inputs and produce versioned outputs for use within automated workflows.

    Python
    Auf GitHub ansehen↗5,452
  • erikbjare/gptmeAvatar von ErikBjare

    ErikBjare/gptme

    4,334Auf GitHub ansehen↗

    gptme is a multi-agent orchestration platform designed for autonomous software engineering, terminal-based AI integration, and RAG-enhanced code navigation. It enables the deployment of persistent agents and specialized subagents to decompose complex tasks and execute parallel technical workflows. The system distinguishes itself through a combination of vision-based GUI automation for controlling desktop applications and surgical patching mechanisms for targeted source code modifications. It utilizes git-based memory management to maintain a versioned history of agent identities, lessons, and

    Chains multiple actions and conditional logic into reusable workflows for complex automation tasks.

    Python
    Auf GitHub ansehen↗4,334
  • opensquilla/opensquillaAvatar von opensquilla

    opensquilla/opensquilla

    4,211Auf GitHub ansehen↗

    OpenSquilla ist ein LLM-Agent-Orchestration-Framework zur Koordination mehrstufiger KI-Workflows und Tool-Ausführungen mittels gerichteter azyklischer Graphen. Es fungiert als zentrales System zur Verwaltung spezialisierter Skill-Pakete und zur Ausführung komplexer Reasoning-Sequenzen. Das Projekt zeichnet sich durch ein Routing-Gateway aus, das Aufgaben basierend auf Komplexität, Kosten und Performance an verschiedene KI-Anbieter weiterleitet. Es nutzt ein mehrstufiges KI-Gedächtnissystem, das Arbeits-, episodisches und semantisches Wissen mittels lokaler Embeddings und SQLite organisiert, sowie eine sichere Ausführungsumgebung (Sandbox), die Agent-generierten Code über risikobasierte Berechtigungsprofile isoliert. Die Plattform deckt ein breites Spektrum an Funktionen ab, einschließlich Multi-Channel-Deployment für Web- und Messaging-Plattformen, automatisierter Aufgabenplanung via Cron und einer Model Context Protocol-Bridge zur Anbindung externer Tools. Zudem bietet sie umfassende Monitoring- und Observability-Tools zur Verfolgung von Token-Kosten, zum Auditing von Laufzeitentscheidungen und zur Verwaltung eines Katalogs wiederverwendbarer Skills. Das System enthält CLI-Utilities für die Workspace-Initialisierung und das Skill-Lifecycle-Management.

    Organizes recurring tasks into reusable and inspectable sequences that can be autonomously discovered.

    Pythonagentaiai-agents
    Auf GitHub ansehen↗4,211
  • atmosphere/atmosphereAvatar von Atmosphere

    Atmosphere/atmosphere

    3,780Auf GitHub ansehen↗

    Atmosphere is a Java-based framework for building and coordinating AI agents. It provides a real-time transport layer for streaming data via WebSockets, SSE, gRPC, and WebTransport, alongside a multi-agent orchestration framework for managing agent fleets through sequential, parallel, and graph-based execution workflows. The project features a durable workflow engine that persists agent state as snapshots, allowing long-running tasks to survive system restarts and incorporate human-in-the-loop approvals. It also implements Model Context Protocol servers to expose tools, resources, and prompt

    Executes multi-step processes that save state and hibernate, resuming without holding system threads.

    Javaacpagentic-aiembabel
    Auf GitHub ansehen↗3,780
  • devoncrawford/video-editing-automationAvatar von DevonCrawford

    DevonCrawford/Video-Editing-Automation

    1,195Auf GitHub ansehen↗

    This project is a toolkit for automating video editing and post-production tasks through programmatic workflows. It functions as a media pipeline that ingests, processes, and exports video content by applying algorithmic logic to assemble raw footage into finished media products. The framework utilizes a library of building blocks to execute repetitive editing operations, allowing for the batch processing of media assets. By mapping temporal metadata and chaining discrete operations into linear pipelines, the system enables the automated assembly of video content without manual intervention.

    Chains discrete algorithmic operations into a linear workflow to automate complex multi-step video assembly and rendering processes.

    C
    Auf GitHub ansehen↗1,195
  1. Home
  2. DevOps & Infrastructure
  3. Automated Workflow Orchestration
  4. Multi-Step Workflow Orchestration

Unter-Tags erkunden

  • Automated Step InjectionExecutes additional background steps before or after function handlers to automate setup, cleanup, or auditing. **Distinct from Multi-Step Workflow Orchestration:** Focuses on injecting steps into the handler lifecycle, distinct from general multi-step orchestration.
  • Inline Step DefinitionsEmbeds task steps directly inside a flow definition for simple, self-contained operations that do not need a separate file. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: focuses on defining steps inline within a flow, not chaining multiple actions.
  • JavaScript Function EvaluationsRuns JavaScript utility functions as workflow steps, conditions, and decision points to orchestrate scanning logic. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: focuses on evaluating JavaScript functions within steps, not general orchestration.
  • Media Processing PipelinesChains of discrete algorithmic operations for automating multi-step video assembly and rendering workflows. **Distinct from Multi-Step Workflow Orchestration:** Distinct from general multi-step workflow orchestration: focuses specifically on media assembly and rendering pipelines.
  • Multi-Host SSH OrchestrationsExecutes commands across multiple remote hosts simultaneously from a single workflow step. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: targets SSH-based multi-host execution, not general multi-step workflow chaining.
  • Multi-Step Fault OrchestratorsRuns faults in sequence or in parallel phases, where multiple faults activate together and recover together. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: focuses on orchestrating fault injection steps in parallel or sequence, not general automation workflows with conditional logic.
  • Reusable Step FragmentsEmbeds reusable step collections called fragments inside modules to avoid repeating common task sequences. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: focuses on reusing step collections, not chaining actions with conditional logic.
  • Stateless LLM OrchestrationLightweight orchestration of stateless LLM calls in multi-step workflows without a dedicated runtime or framework. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: focuses on stateless LLM call sequencing rather than general automation with conditional logic.
  • Step Success Action TriggersRuns logging, variable export, or notification actions automatically when a step completes without error. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: focuses on success-specific actions, not general multi-step chaining.
  • Switch Case Step RoutingsRoutes workflow execution to different steps based on a variable's value using switch/case decision blocks. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: focuses on variable-based routing to specific steps, not general multi-step chaining.
  • Threadless Workflow HibernationMulti-step workflow execution that persists state and pauses without consuming active threads. **Distinct from Multi-Step Workflow Orchestration:** Specifically emphasizes the 'threadless' nature of pausing and resuming via state snapshots.
  • Workflow Definition MergersReplaces, prepends, appends, or merges steps and modules when one workflow inherits from another. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: focuses on the merge strategies during inheritance, not general multi-step chaining.
  • Workflow Inheritance MergingReplaces, prepends, appends, or merges steps and modules when one workflow inherits from another. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: focuses on merging inherited workflow definitions, not general multi-step orchestration.
  • YAML Step DefinitionsAssembles sequential or parallel steps using shell commands, HTTP requests, LLM calls, or JavaScript functions in YAML. **Distinct from Multi-Step Workflow Orchestration:** Distinct from Multi-Step Workflow Orchestration: focuses on defining individual step types in YAML, not general orchestration.