#248 · Primary category: AI Agents & Automation

flowgram.ai

ai automation coze data-flow diagram flow flowchart graph integration-framework javascript no-code node-based-ui react typescript typescript-library visualization workflow workflow-automation

FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials that helps developers build AI workflow platforms faster and simpler.

Project last updated:08/20/26

GitHub Stars

8.4K

Forks

763

Contributors

28

License

MIT

Why we included this project

Building a visual workflow builder for AI agents means a lot of unglamorous work: a node canvas, forms for configuring each step, variable scoping across nested loops, and reusable blocks for LLM calls, conditions, and code. FlowGram packages that into a React/TypeScript framework, so a team can assemble a Coze-style platform without rebuilding the graph editor and property forms from scratch. It is deliberately a toolkit, not a finished product; you supply the backend, execution engine, and data model while FlowGram handles the interactive editor surface. The bundled free-layout demo, which walks a list of cities through HTTP calls, a Code node, an LLM, and a Condition before aggregating results, gives a quick sense of what comes out of the box.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category