Download
FlowGram is an open-source, node-based workflow development framework and toolkit aimed at helping developers build custom AI-workflow platforms or automation systems through a visual, drag-and-drop interface. Instead of shipping as a ready-made product, it provides the building blocks — a canvas for wiring together nodes, a form engine for configuring node parameters, a variable-scope and type-inference engine, and a set of “materials” (pre-built node types such as code execution, conditional logic, LLM calls, etc.) that can be composed into larger workflows. This makes FlowGram highly flexible: you can prototype data-processing pipelines, AI-agent flows, automation scripts, or even business process automation without writing all the plumbing yourself. The framework supports both free-layout canvases (for free-form graphs) and fixed-layout canvases (for more structured flowcharts, including loops, branches, compound nodes), giving you visual freedom depending on your use-case.
Features
- Visual node-based workflow builder with draggable canvas supporting both free-layout (free-form node placement) and fixed-layout (structured flowcharts with loops/branches) canvases
- Built-in form engine for node configuration: supports parameter editing, validation, side-effects, data binding, and error capturing
- Variable engine with scope management, type inference, and data-flow tracking, enabling safe and clear handling of data across node connections
- Pre-made “materials” (node types) like code execution, conditional logic, LLM invocation, HTTP requests, loops/branches — allowing complex workflows without writing boilerplate from scratch
- Modular, extensible and open-source architecture (MIT license), enabling developers to add custom node types, integrate external tools or services, or embed FlowGram in larger applications
- Actively maintained project with frequent commits, generous community adoption (thousands of stars & forks), and a clear release/versioning schedule — suitable for production use or serious prototypes
Project Samples
