Open source alternatives to Prompt → Diagram
200 open source apps like Prompt → Diagram, closest match first.
Top picks
- C

ChatLLM-Web
LaunchChatLLM 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
- F
Fireworks Tech Graph
Launchfireworks-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
- G

Graphologue
LaunchGraphologue creates interactive diagrams for GPT-5.4 responses in real time. Learn more about the project in our UIST 2023 paper.
FreeOpen source
- G
Gpt2 Webgl
LaunchA browser-based, WebGL2 implementation of GPT-2 with transform block and attention matrix visualization
FreeOpen source
- C
CharDesk
LaunchCharDesk 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
- L
LangGraph-GUI
LaunchVisual node-edge graph GUI editor for LangGraph and run with local LLM or online API
FreeOpen sourceSelf-hosted
More like Prompt → Diagram
Next AI Draw.io
A next.js web application that integrates AI capabilities with draw.io diagrams
Text To Diagram Site
Compare syntax, layouts, outputs between languages for generating diagrams
TwitCanva-Video-Workflow
A next-generation AI-powered infinite canvas workspace built for creators
About Prompt → Diagram
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

