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.
Awesome AI Agents › AI Workflow Orchestrators
InfinitiBit/graphbit
GraphBit is an open-source framework for building and running agent workflows that are described as directed graphs of typed nodes. The execution core is written in Rust and exposed through a thin Python layer, so workflow definition happens in Python while scheduling, concurrency and state handling happen in native code. Nodes can call large language models, invoke tools chosen by the model from tool descriptions, or run plain transformations, and several branches of a graph can execute in parallel while memory is carried across steps. The project targets deterministic and low-overhead execution: it ships retry policies, circuit breakers, error handling and fault recovery so that a failing step does not abort a whole run, plus concurrency limits and memory controls for long running workloads. Observability is part of the runtime, with tracing, structured logs and performance metrics collected during execution. Model access is provider agnostic and covers OpenAI, Azure OpenAI, Anthropic, OpenRouter, DeepSeek, Replicate, Ollama and TogetherAI among others, which lets the same graph run against hosted or local models. The maintainers publish an internal benchmark suite comparing GraphBit with Python-native agent frameworks on identical workloads and report substantially lower CPU and memory use at comparable throughput; those numbers come from the project itself and are not independently verified here. Distribution is through PyPI, and the documentation site covers workflow construction, node types, provider configuration and deployment. The framework is aimed at engineers who already know how to prompt models but need the surrounding execution layer to behave predictably in production, and at teams running agent workloads on constrained hardware or edge machines where the resource footprint of a Python-only orchestration stack is a problem.
https://github.com/InfinitiBit/graphbit
Also in AI Workflow Orchestrators
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.