
MASFactory is an open-source Python framework for developers building workflows in which multiple AI agents work together. Its Vibe Graphing feature drafts a collaboration graph from a plain-language description, then lets people refine and approve the design through dialogue before it becomes an executable workflow. The license is Apache 2.0.
The graph makes agent relationships and message flow explicit. Workflows can include nested subgraphs, repeated review or testing loops, and branches that route tasks by conditions or model decisions. Reusable components let developers carry a collaboration pattern into another workflow rather than rebuild it each time.
MASFactory Visualizer provides graph previews, drag-and-drop editing, and traces of node status, messages, and shared state during execution. Developers can also define workflows in code. These authoring methods share one runtime, so a graph drafted through conversation can be visually edited and traced as it runs. Human steps can pause a workflow for confirmation, input, file review, or editing.
Its ContextBlock protocol organizes agent memory, retrieval-augmented generation (RAG), and Model Context Protocol (MCP) sources. Agents can receive context automatically or retrieve it when needed; adapters connect context and communication capabilities with external frameworks.
Separate hosted demos show research workflows: NowWhat produces AI paper briefings, while OhNoPPT turns research papers into editable PowerPoint files. Their workflow code is available in the repository for reuse and study.
Claim this page with an email at masfactory.dev. MASFactory gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find MASFactory?Promote it
Something wrong or outdated on this page?
157.7KUpdated 6 hours ago
Docker · Web#Code execution#MCP#OpenAI-compatible API
Dify is a source-available platform for teams building AI agents and apps on a visual canvas. Its Community Edition runs on your own server with Docker. Dify also offers a hosted cloud service, while Enterprise deployments can run in a VPC or on a self-hosted server. The Community Edition uses a custom Apache 2.0 derivative license.
28.5KUpdated 8 hours ago
Web#Human approval#LLM tracing#MCP
18KUpdated 8 hours agoMIT
Docker · VS Code#LLM tracing#MCP#Multi-agent workflows
29.8KUpdated 14 hours agoApache-2.0
macOS · Docker · Web#Code execution#LLM tracing#Multi-user access
10.7KUpdated 4 days agoMIT
Web#Guardrails#Human approval#LLM tracing
240Updated 1 day ago
#Agent Skills#Code execution#Git integration
Mastra is a TypeScript framework for developers building AI agents and applications on their own servers or inside existing web apps. Its server runs locally or as a standalone deployment; Mastra Cloud provides a hosted alternative. Model routing connects to providers such as OpenAI, Anthropic, and Gemini, so running the framework locally doesn't keep those model requests on your machine.
RocketRide is a self-hosted AI pipeline builder and runtime for developers building document search, data processing, and AI agent workflows. Its visual editor lives in VS Code, so you can design and debug workflows alongside your application code. The engine is free and open source under the MIT license.
Sim is an AI agent workspace for teams that need to build automations and control how people use them across an organization. You can self-host it on your own server or cloud with Docker or Kubernetes. Its open-source code uses the Apache 2.0 license.
VoltAgent is an MIT-licensed TypeScript AI agent framework for developers building assistants and automated workflows. It pairs code-based agent development with VoltOps, a console for inspecting execution and managing agents. The console can run on your own server or as a cloud service; managed deployment uses hosted infrastructure.
Pi Extensible Workflows is an extension for developers who want Pi to coordinate several AI agents through repeatable, resumable workflows. The orchestration runs in your Pi host environment using Node.js, with the same access to files and processes as Pi. Its workflow scripts define task order, parallel work, and approval checkpoints.