bytedance/flowgram.ai

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.

What it solves

FlowGram provides a development framework and toolkit for developers who want to build their own AI workflow platforms. Instead of being a finished application, it offers the necessary building blocks—like a visual canvas and variable management—to create a custom environment where users can design complex AI processes visually.

How it works

It functions as a composable toolkit that integrates several core engines:

  • Canvas Engines: Offers both a "Free Layout" (nodes placed anywhere) and a "Fixed Layout" (structured positions with support for loops and branches).
  • Form Engine: Handles the creation, validation, and editing of node configurations.
  • Variable Engine: Manages data flow through scope constraints, type inference, and structure inspection.
  • Materials: Provides ready-to-use components such as LLM nodes, condition gates, and code editors.

Who it’s for

Software developers building AI agent platforms, workflow automation tools, or any application that requires a visual, node-based interface for designing logic flows.

Highlights

  • Visual Workflow Development: Supports both free-form and structured layouts for designing logic.
  • Variable Scope Chain: Simplifies data management across different nodes in a workflow.
  • Extensible Toolkit: Includes built-in materials for LLMs and code execution to accelerate platform development.
  • Integration Ready: Used by projects like Coze Studio for AI agent development.

Related

  • Project
    chatfire-AI/huobao-canvas

    A visual AI creation canvas that allows users to orchestrate text-to-image and video generation workflows using a node-based interface.

  • Project
    Comfy-Org/ComfyUI

    A modular, node-based AI engine for visual professionals to create complex workflows for generating images, video, audio, and 3D models with precise parameter control.

  • Project
    vercel-labs/workflow-builder-template

    A template for building AI-driven workflow automation platforms, featuring a visual drag-and-drop builder that generates executable TypeScript code.

  • Project
    GizClaw/flowcraft

    FlowCraft is a Go toolkit that provides modular, provider‑agnostic libraries for building AI agents, memory stores, and runtime pipelines. It defines core contracts (agent, graph, tool, inference, memory, event bus) and supplies adapters for major LLM providers, SQLite checkpoint storage, and sandboxed execution. A runnable demo (`examples/forge`) shows how to assemble a workspace from a YAML deployment, run an interactive TUI, and execute scripted tests. The project is actively maintained, MIT‑licensed, and intended for Go developers who want a flexible, non‑vendor‑locked foundation for AI applications.

  • Project
    FlowiseAI/Flowise

    A visual drag-and-drop builder for creating and deploying AI agents and workflows without writing code.