#4848th of 118 in Agent frameworks and SDKs
flowgram.ai
TypeScript toolkit for embedding visual workflow editors in your own product
- Stars
- 8.6k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Oct 2026
- Language
- TypeScript
7,867 on 20 Apr 20268,573 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
FlowGram is a set of TypeScript packages for building a node-based workflow editor: free-layout and fixed-layout canvases, a node form engine, and a variable scope engine with type inference. It includes prebuilt nodes such as LLM, Condition and Code Editor. A separate FlowGram Desktop preview for macOS and Windows builds and runs workflows through chat and a canvas.
Who it is for: Front-end developers embedding a visual workflow editor in an AI platform
Strengths
- Two canvas modes: free layout and fixed layout with branch and loop nodes
- Form engine covers validation, linkage and side effects for node config
- Variable engine provides scope chains and type inference across nodes
- Scaffold with npx @flowgram.ai/create-app; MIT license; used by Coze Studio
Weaknesses
- Front-end toolkit, not a hosted workflow server; you build the platform around it
- Desktop app is a preview; installers are unsigned and macOS builds not notarized
- Desktop installers listed only for macOS and Windows, no Linux build
What it needs
- no GPU
- Needs Node.js, npm
- port 3000
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Quick answers
Is flowgram.ai open source?
Yes. Its code is on GitHub under the MIT license.
Does flowgram.ai need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 118| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |