Skip to content
Prompt → Diagram

Free alternatives to Prompt → Diagram

200 free apps like Prompt → Diagram, closest match first.

Top picks

  1. C

    ChatLLM-Web

    Launch

    ChatLLM is a local AI workspace that runs language models directly in your web browser. It uses WebGPU, so the model runs on your own device and conversations are not sent to a remote server. The default model is Qwen 3.5 2B, described as a

    FreeOpen source

  2. F

    Fireworks Tech Graph

    Launch

    fireworks-tech-graph is an open-source Agent Skill that turns a natural language description into a technical diagram. It works unchanged in Codex and Claude Code, and it produces SVG as the main artefact, with PNG export, offline interacti

    FreeOpen source

  3. G

    Graphologue

    Launch

    Graphologue creates interactive diagrams for GPT-5.4 responses in real time. Learn more about the project in our UIST 2023 paper.

    FreeOpen source

  4. G

    Gpt2 Webgl

    Launch

    A browser-based, WebGL2 implementation of GPT-2 with transform block and attention matrix visualization

    FreeOpen source

  5. C

    CharDesk

    Launch

    CharDesk is a canvas for drawing diagrams, visual explanations and interface sketches out of Unicode characters. The canvas is infinite, and what you draw is stored as editable text, so the scene you see can also be read and changed by an A

    FreeOpen source

  6. A

    AgentOp

    Launch

    AgentOp lets you build AI agents that run entirely in your browser. Open models — Llama, Qwen, Gemma, Phi, DeepSeek and more — load locally with WebGPU. No install, no server, no API key: your prompts and data never leave the tab.

    Free

More like Prompt → Diagram

7
L

LangGraph-GUI

Visual node-edge graph GUI editor for LangGraph and run

Launch
8
S

Smart Draw

Draw any professional and beautiful diagram you can imagine in the simplest way

Launch
9
S

Snip

The visual communication layer between humans and AI agents

Launch
10
N

Next AI Draw.io

A next.js web application that integrates AI capabilities with draw.io diagrams

Launch
11
S

Sipp

AI inference, packed simply

Launch
12
E

excalidraw

User requests diagrams, flowcharts, architecture charts, or visualizations

Get
13
S

show-me

Help the user understand the current topic visually

Get
14
O

OpenFlowKit

Free, open-source diagram canvas

Launch
15
F

Flowchart AI

Turn any idea into a flowchart in one click

Launch
16
F

fireworks-tech-graph

Create precise SVG technical diagrams, export PNG or offline HTML

Get
17
O

Oh My Mermaid

Turn complex codebases into clear, navigable architecture diagrams

Launch
18
E

excalidraw-skill

Programmatic canvas toolkit for creating, editing

Get
19
A

Archscribe

Premium hand-drawn, dark-background animated architecture & process diagrams

Launch
20
G

Google AI Edge Eloquent

Free on-device AI dictation and voice editing from Google

Launch
21
D

draw.io

Create diagrams in chat, rendered as live interactive draw.io diagrams

Get
22
H

hustcc/mcp-mermaid

Generate Mermaid diagrams and charts dynamically

Get
23
M

microcharts

Word-sized charts for React, made for LLMs and humans

Launch
24
W

WebAI-to-API

Webchat to API

Launch
25
W

Web LLM

High-performance In-browser LLM Inference Engine

Launch
26
G

Guaardvark

Self-hosted AI studio on your own GPU: chat with your files

Launch
27
C

ChromeAI Gemini Chatbot

Run Chrome built-in large language model AI locally in your browser

Launch
28
E

excalidraw-diagram

Create Excalidraw diagram JSON files that make visual arguments

Get
29
B

baoyu-diagram

Create professional, dark-themed SVG diagrams of any type

Get
30
A

architecture-diagram

Create polished dark-themed architecture diagrams as self-contained HTML+SVG

Get
31
T

Text To Diagram Site

Compare syntax, layouts, outputs between languages for generating diagrams

Launch
32
D

drawio

Create, edit, replicate, import, and export draw.io diagrams

Get
33
A

archify

Create validated architecture, workflow, sequence, data-flow, lifecycle/state

Get
34
T

Terravision

Cloud architecture diagrams in both directions: AI prompt or JSON to diagram

Launch
35
O

OnUml

AI-Powered Mermaid UML Generator

Launch
36
D

drawio-skill

Create, edit, synchronize, inspect, test, and publish editable draw.io diagrams

Get
37
E

excalidraw-diagram

Generate Excalidraw diagrams from text content

Get
38
E

eraser-diagrams

Generates architecture diagrams from code, infrastructure, or descriptions

Get
39
C

Claude Canvas

AI-orchestrated visual production for Obsidian Canvas

Launch
40
D

docs-canvas

Render a documentation-style Cursor Canvas

Get
41
V

vgpu

Build, debug, test, and optimize WebGPU projects

Get
42
A

architecture-diagrams

Create system architecture diagrams

Get
43
H

https://cloudairy.com/

A collaborative workspace for creating animated architecture diagrams

Launch
44
T

tldraw-skill

User requests diagrams, flowcharts, architecture charts, or visualizations

Get
45
M

manim-video

Build reusable Manim explainers for technical concepts, graphs, system diagrams

Get
46
M

MiniCPM5-2B WebGPU Pi

A coding agent running entirely in your browser

Launch
47
L

LocalMode

Run AI entirely in your browser, no servers or API keys

Launch
48
P

pretty-mermaid

Generate and render Mermaid diagrams for architecture docs, READMEs, PRs

Get
49
D

Drawthe.net

drawthe.net draws network diagrams dynamically

Launch
50
B

beautiful-mermaid

Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library

Get

About Prompt → Diagram

P

Prompt → Diagram

Gemma 4 E2B in desktop Chrome (WebGPU)

Prompt to Diagram is a browser demo that turns a text description into an Excalidraw diagram. You describe a system, a flow or a schema, and the Gemma 4 E2B language model writes a short piece of code that is rendered as an editable Excalidraw drawing. The model runs on your own machine through WebGPU, and the page says everything happens in your browser. The demo includes sample prompts such as an OAuth sequence diagram, a CI/CD pipeline, a TCP state machine, an e-commerce schema, payment classes and a checkout swimlane. To reduce memory use, it compresses the model's KV cache about 2.4 times with a TurboQuant-style algorithm rewritten as WGSL compute shaders, which the page says lets longer conversations fit in GPU memory. It needs desktop Chrome 134 or newer with WebGPU subgroups and roughly 3 GB of RAM, and it does not run on Safari or iOS yet. A related turboquant-wasm package, published on npm and GitHub, implements the same algorithm in WASM for vector search on the CPU.

Category
AI
Website
teamchong.github.io