discover · compare · collections · requirements · contribute · feed · watching · stats · help with your tokens
bytedance/flowgram.ai · source
Snapshot 0 · 2026-11-04T12:47:27Z · TypeScript · MIT
Content fingerprint
b7df01a7f1648b8db1445faeb341a44fcc83db63c8fc97d4eb528bb6f0086e2eGitHub description at capture
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.
README at capture
 <div align="center"> [](https://github.com/bytedance/flowgram.ai/blob/main/LICENSE) [](https://www.npmjs.com/package/@flowgram.ai/editor) [](https://deepwiki.com/bytedance/flowgram.ai) [](https://juejin.cn/column/7479814468601315362) [](https://trendshift.io/repositories/13877) </div> # FlowGram｜Workflow development framework [English](README.md) | [中文](README_ZH.md) | [Español](README_ES.md) | [Русский](README_RU.md) | [Português](README_PT.md) | [Deutsch](README_DE.md) | [日本語](README_JA.md) FlowGram is a composable, visual, easy-to-integrate, and extensible workflow development framework & toolkit. Our goal is to help developers build AI workflow platforms **faster** and **simpler**. FlowGram comes with a suite of built-in tools for workflow development: flow canvas, node configuration form, variable scope chain, and ready-to-use materials (LLM, Condition, Code Editor etc). The framework packages provide the building blocks for your own workflow platform; FlowGram Desktop brings them together in a native Agent workspace. Learn more at [FlowGram.AI 🌐](https://flowgram.ai) ## 🖥️ FlowGram Desktop FlowGram Desktop is a native Agent workspace for macOS and Windows. Build, run, debug, and reuse workflows through conversation and a visual canvas. - **Build:** describe a task in chat, then refine nodes, conditions, parallel branches, joins, and loops on the canvas. - **Debug:** test individual nodes, inspect inputs and outputs, and revisit execution paths and historical workflow snapshots. - **Reuse:** publish versioned workflows for HTTP and MCP consumers, or call them from other workflows. - **Organize:** manage project-based workflows and chats, import and export projects, and work in English or Simplified Chinese with light and dark themes. Six industry example projects help you get started. <https://github.com/user-attachments/assets/48c0e187-5bd8-40b2-9a96-60d3839db170> ### Download Desktop **macOS — install with one command** (Apple Silicon and Intel): ```sh curl --fail --silent --show-error https://flowgram.ai/desktop/install.sh | sh ``` Paste into Terminal to download the latest preview, verify its SHA-256 checksum, and install FlowGram. The script removes quarantine only from the installed app so the unsigned preview can open. No `sudo` is required. Run the same command to update; quit FlowGram first. [⬇ Latest preview release](https://github.com/bytedance/flowgram.ai/releases/tag/desktop-preview) Choose your platform to download the latest preview. These permanent links are updated automatically after all three platform builds succeed. | Platform | Download | | --- | --- | | macOS · Apple Silicon (ARM64) | [Download DMG](https://github.com/bytedance/flowgram.ai/releases/download/desktop-preview/FlowGram_aarch64-apple-darwin.dmg) | | macOS · Intel | [Download DMG](https://github.com/bytedance/flowgram.ai/releases/download/desktop-preview/FlowGram_x86_64-apple-darwin.dmg) | | Windows 10/11 · x64 | [Download EXE](https://github.com/bytedance/flowgram.ai/releases/download/desktop-preview/FlowGram_x86_64-pc-windows-msvc-setup.exe) | Download the installer directly; no GitHub sign-in is required. Open the .dmg on macOS or run the setup .exe on Windows. Checksums and build information are available on the release page. Preview installers are unsigned; macOS builds are not notarized. ## 🎬 Demo <https://github.com/user-attachments/assets/fee87890-ceec-4c07-b659-08afc4dedc26> Open in [CodeSandbox 🌐](https://codesandbox.io/p/github/louisyoungx/flowgram-demo/main) or [StackBlitz 🌐](https://stackblitz.com/~/github.com/louisyoungx/flowgram-demo) In this demo, we iterate through a list of cities, fetch real-time weather via HTTP, parse temperatures with a Code node, generate outfit suggestions with an LLM, gate by a Condition, aggregate results across the loop, and finally use an Advisor LLM to pick the most comfortable city before sending the result to the End node. ## 🚀 Quick Start 1. Create a new FlowGram project: ```sh npx @flowgram.ai/create-app@latest ``` > We recommend choosing the `Free Layout Demo ⭐️` template. 2. Start the project: ```sh cd demo-free-layout npm install npm start ``` 3. Open [http://localhost:3000](http://localhost:3000) in your browser. ## ✨ Features | Feature | Description | Demo | | -------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------- | | [Free Layout Canvas](https://flowgram.ai/examples/free-layout/free-feature-overview.html) | Free layout canvas where nodes can be placed anywhere and connected using free-form lines. |  | | [Fixed Layout Canvas](https://flowgram.ai/examples/fixed-layout/fixed-feature-overview.html) | Fixed layout canvas where nodes can be dragged to specified positions, with support for compound nodes like branches and loops. |  | | [Form](https://flowgram.ai/examples/node-form/basic.html) | The form engine manages the CRUD operations of node data and provides rendering, validation, side effects, linkage, and error-capturing capabilities, simplifying the development of node configurations. |  | | [Variable](https://flowgram.ai/guide/variable/basic.html) | The variable engine supports scope constraints, variable structure inspection, and type inference, making it easy to manage data flow within the workflow. |  | ## 📖 Documentation You can find the FlowGram documentation [on the website](https://flowgram.ai). The documentation is divided into several sections: - [Quick Start](https://flowgram.ai/guide/getting-started/introduction.html) - [Canvas](https://flowgram.ai/guide/free-layout/load.html) - [Form](https://flowgram.ai/guide/form/form.html) - [Variable](https://flowgram.ai/guide/variable/basic.html) - [Material](https://flowgram.ai/materials/introduction.html) - [Runtime](https://flowgram.ai/guide/runtime/introduction.html) - [Advanced Guides](https://flowgram.ai/guide/advanced/zoom-scroll.html) - [API Reference](https://flowgram.ai/api/index.html) - [Where to get Support](https://flowgram.ai/guide/contact-us.html) - [Contributing Guide](https://flowgram.ai/guide/contributing.html) ## 🙌 Contributors [](https://github.com/bytedance/flowgram.ai/graphs/contributors) ## 🌍 Adoption - [Coze Studio](https://github.com/coze-dev/coze-studio) is an all-in-one AI agent development tool. Providing the latest large models and tools, various development modes and frameworks, Coze Studio offers the most convenient AI agent development environment, from development to deployment. - [NNDeploy](https://github.com/NNDeploy/nndeploy) is a workflow-based multi-platform ai deployment tool. - [Certimate](https://github.com/certimate-go/certimate) is an open-source SSL certificate management tool that helps you automatically apply for and deploy SSL certificates with a visual workflow. It is one of the ACME client options listed in the official documentation of Let's Encrypt. ## 📬 Contact us - Issues: [Issues](https://github.com/bytedance/flowgram.ai/issues) - Lark: Scan the QR code below with [Register Feishu](https://www.feishu.cn/en/) to join our FlowGram user group. <img src="./apps/docs/src/public/lark-group.png" width="200"/>