Awesome AI AgentsAI Workflow Orchestrators

PrefectHQ/marvin

⭐ 6197 Python repository created 2023-03-10

Marvin is a Python framework designed to build agentic AI workflows that provide a structured and developer-focused approach to defining workflows and delegating tasks to large language models (LLMs) while maintaining control and transparency. The framework allows users to create discrete, observable tasks that describe specific objectives, assign specialized AI agents to these tasks, and combine tasks into threads to orchestrate more complex behaviors. Marvin supports structured-output utilities such as extracting, casting, classifying, and generating structured data from unstructured input, making it easier to work with AI-generated content in a type-safe manner. The framework introduces agentic control flow, enabling users to run tasks simply or define specialized agents with specific instructions to complete tasks. Tasks can be explicitly defined with instructions and expected result types, and they can utilize custom tools to interact with code and data, making the workflows highly customizable and observable. Marvin emphasizes a task-centric architecture, specialized agents, type-safe results, flexible control, multi-agent orchestration, thread management, ecosystem integration, and developer speed. Marvin is currently under active development with version 3.0, which may have breaking changes and evolving documentation. It supports multiple AI models, including OpenAI by default and other Pydantic AI models. The framework aims to spark joy in working with AI by providing a balance between control and autonomy, enabling developers to start simple and scale up their AI workflows efficiently. It is suitable for developers looking to build complex AI-driven applications with clear task management and agent orchestration capabilities.

https://github.com/PrefectHQ/marvin

agentic-ai-workflowsagentic-control-flowagentsaiai-agentsai-functionsai-workflowsambient-aichatbotsdeveloper-focusedgptllmllmsmarvin.agentmarvin.castmarvin.classifymarvin.extractmarvin.generatemarvin.runmarvin.taskmulti-agent-orchestrationnliopenaipydantic-ai-modelspythonpython-frameworkspecialized-ai-agentsstructured-output-utilitiestasksthread-managementthreadstype-safe-results

Also in AI Workflow Orchestrators

langflow-ai/langflow

Langflow is a powerful open-source platform for building, testing, and deploying AI-powered agents and workflows with visual authoring, multi-agent orchestration, and API integration capabilities.

stablyai/orca

Orca is an AI Orchestrator that provides an integrated development environment for running and managing parallel AI agents across various platforms, including desktop and mobile.

calesthio/OpenMontage

OpenMontage is an open-source, agentic video production system that transforms AI coding assistants into full video studios for automated video creation from text prompts.

stanfordnlp/dspy

DSPy is a framework that enables programming language models with compositional Python code to build modular AI systems and optimize their performance beyond traditional prompting methods.

kestra-io/kestra

Kestra is an open-source, event-driven orchestration platform for data, AI, and infrastructure workflows, enabling declarative and code-based automation with a rich plugin ecosystem.

humanlayer/12-factor-agents

12 Factor Agents is a comprehensive framework outlining principles for building reliable, scalable, and production-ready LLM-powered AI software agents.

yoheinakajima/babyagi

BabyAGI is an experimental framework for building self-building autonomous agents using a function-centric approach with comprehensive management, logging, and a dashboard interface.

teableio/teable

Teable is an AI spreadsheet platform that integrates data management, AI workflows, and app building on a PostgreSQL backend, enabling users to create custom business applications.