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
agent-sh/agentsys
AgentSys is a modular runtime and orchestration system for AI coding agents. Its premise is that generating code is no longer the hard part, and that the surrounding work needs automating: task selection, branch management, code review, artifact cleanup, CI, pull request comments and deployment. The project supplies structured pipelines, gated phases, specialised agents and state that persists across session boundaries so interrupted work can resume. The current release counts 24 plugins, 49 agents split between file-based definitions and role-based specialists, and 44 skills, backed by roughly 30,000 lines of library code and several thousand tests. Each plugin lives in its own standalone repository under the agent-sh organisation, while the agentsys package acts as marketplace and installer that fetches them automatically. Every agent has one responsibility, an assigned model and defined inputs and outputs, and pipelines enforce phase gates so steps cannot be skipped. The design principle stated by the author is that deterministic code should do deterministic work and the model should only be called where judgement matters: detection uses regex, AST and static analysis, while LLM calls are reserved for synthesis, planning and review. The authors report this cuts token use substantially for one of the analysis commands compared with a multi-agent approach. Findings carry certainty levels of high, medium and low, which map onto safe auto-fix, needs context and needs human judgement, a scheme derived from testing across more than a thousand repositories. Published benchmarks compare Claude Opus and Sonnet with and without the pipeline on documentation and onboarding tasks, arguing that structured prompts and enriched repository context narrow the gap between model tiers and lower cost. AgentSys runs on Claude Code, OpenCode, Codex CLI, Cursor and Kiro, installs through the marketplace or an npm installer, is written in JavaScript and is MIT licensed.
https://github.com/agent-sh/agentsys
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.