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
mikeyobrien/ralph-orchestrator
Ralph Orchestrator implements the Ralph Wiggum technique, which pursues autonomous task completion by running an AI coding agent in a continuous loop until it emits LOOP_COMPLETE or reaches an iteration limit. It is written in Rust, distributed as the ralph-cli binary through npm, Cargo or a GitHub Releases installer, and driven from the command line. A typical flow is to initialise with a chosen backend, run an interactive planning session that writes requirements, design and implementation-plan documents under .ralph/specs, and then run the implementation loop against that specification; for simpler work the planning stage can be skipped and a prompt passed directly. Supported backends include Claude Code, Kiro, Gemini CLI, Codex, Forge, Amp, Copilot CLI and OpenCode. The central abstraction is the hat system, a set of specialised personas that coordinate through events, with five supported builtins named code-assist, debug, research, review and pdd-to-code-assist plus further documented example patterns. Backpressure gates reject incomplete work by enforcing tests, lint and typecheck, while memories and task tracking give the loop persistent learning and runtime work state. Ralph can itself run as an MCP server over stdio, scoped to a single workspace root resolved from a flag, an environment variable or the working directory, with the recommendation to run one instance per repository. An alpha web dashboard combines a Rust RPC API with a frontend for monitoring and managing loops, requiring a Rust toolchain and Node 18 or newer. Human-in-the-loop support arrives through RObot, a Telegram bridge in which agents emit human.interact events and block until answered, while people can send proactive guidance mid-loop, route messages to parallel loops by reply or loop-id prefix, and issue status, tasks and restart commands.
https://github.com/mikeyobrien/ralph-orchestrator
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.