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
lofcz/LLMTornado
LLM Tornado is a .NET toolkit for building AI agents and workflows against many model providers through one strongly typed API. It ships its own connectors instead of depending on first-party vendor SDKs, covering OpenAI, Anthropic, Google, Azure, Mistral, Cohere, DeepSeek, Groq, xAI, OpenRouter, Perplexity and roughly twenty more, and a published feature matrix tracks which endpoints and provider-specific features each connector exposes. Local deployments are treated as equal citizens, with support for vLLM, Ollama and LocalAI including request transformations. The orchestration layer is built on three concepts: an Orchestrator that is the graph, a Runner that is a node and an Advancer that is an edge. On top of these it provides agent handoffs, parallel execution, a builder pattern for assembling graphs and Mermaid export so a workflow can be inspected as a diagram. Because pipelines are written once and bound to a provider only by model name, the same workflow can be moved between vendors without a rewrite. The SDK is fully multimodal across text, images, video, documents, URLs and audio, and separate NuGet packages add Model Context Protocol client support, Agent2Agent communication between agents on different platforms, and Anthropic-style skills that load folders of instructions and scripts on demand. Vector database connectors cover Chroma, PgVector, Pinecone, Faiss and Qdrant for retrieval-augmented pipelines. Integration with Microsoft.Extensions.AI lets Tornado slot into Semantic Kernel applications, and features aimed at production include a guardrails framework, request preview and transformation before a call is committed, OpenTelemetry instrumentation and stable APIs. The project is MIT licensed and aimed at .NET developers who want one dependency for chat, agents, retrieval and tool protocols rather than a separate library per provider.
https://github.com/lofcz/LLMTornado
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.