Skip to content
Prompt → Diagram

Self-hosted alternatives to Prompt → Diagram

200 self-hosted apps like Prompt → Diagram, closest match first.

Top picks

  1. L

    LangGraph-GUI

    Launch

    Visual node-edge graph GUI editor for LangGraph and run with local LLM or online API

    FreeOpen sourceSelf-hosted

  2. S

    Sipp

    Launch

    AI inference, packed simply. A blazing-fast, zero-dependency WebGPU runtime to run GGUF models directly in the browser. Features a symmetric API for seamless local execution and cloud provider routing. Built with Rust & C++.

    FreeOpen sourceSelf-hosted

  3. O

    OpenFlowKit

    Launch

    Free, open-source diagram canvas. Draw it, write it as code (Mermaid, D2, Structurizr in), ask any AI model or a local one, let Claude Code edit it live over MCP, or map a GitHub repo with every arrow cited to a file and line. MIT, local-fi

    FreeOpen sourceSelf-hosted

  4. G

    Guaardvark

    Launch

    Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local video, image, music and voice generation. No telemetry.

    FreeOpen sourceSelf-hosted

  5. N

    Netron

    Launch

    This Snap is deprecated. Please migrate to .deb or .rpm. https://github.com/lutzroeder/netron/issues/1500

    FreeOpen sourceSelf-hosted

  6. M

    MindGeniusAI

    Launch

    An AI agent that reads your PDFs and draws editable mind maps — visible tool-calling loop, built-in RAG, bring-your-own-key, multi-provider (OpenAI / Claude / DeepSeek / Kimi). Self-hostable.

    FreeOpen sourceSelf-hosted

More like Prompt → Diagram

7
K

Knowledge Graph Extractor

Turn any document or a whole zip into an interactive knowledge graph

Launch
8
F

FossFLOW

Make beautiful isometric infrastructure diagrams

Launch
9
A

Agentic Signal

Visual AI agent workflow automation platform with local LLM integration

Launch
10
D

Drafft Ink

Effortlessly self-host whiteboards

Launch
11
P

ProductFlow

gpt-image-2 画图工作台 / Self-hosted workbench for AI copy, posters, image sessions

Launch
12
A

Airunner

Offline inference engine for art, real-time voice conversations

Launch
13
G

Gemini Web2api Go

Gemini web → OpenAI-compatible API, self-hosted, no API key

Launch
14
L

LoomFlow

Lightweight AI-native workflow builder for individuals and small teams

Launch
15
O

overtchat

A simpler self-hosted alternative to Open WebUI

Launch
16
M

Mix-Studio

The cleanest, responsive AI workspace

Launch
17
S

SourceWeft

Open-source, self-hostable alternative to ChatGPT and NotebookLM

Launch
18
D

Duragraph

Self-hosted, enterprise-ready AI workflow orchestration

Launch
19
E

Excalidraw Full

Your Self-Hosted, Cloud-Ready Collaboration Platform

Launch
20
D

Draw.io

Create complex diagrams, collaborate

Launch
21
L

Locally Uncensored

The all-in-one local AI studio for your desktop: chat

Launch
22
L

Llmaker

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Launch
23
S

Silo

多模型同时对话、文生图,纯前端。Multi-model simultaneous chat、text-to-image generation

Launch
24
C

Comma

Best free & open source AI personal assistant

Launch
25
P

Pocketpaw

Your AI agent in 30 seconds

Launch
26
P

Pipelex

Build AI methods with your coding agent

Launch
27
E

Eclaire

Local-first, open-source AI assistant for your data

Launch
28
G

GrayMatter

30 sec to give your AI agents persistent memory

Launch
29
L

Local-Multimodal-AI-Chat

Self-hostable multimodal chat with local LLMs

Launch
30
W

Webchat2api

OpenAI-compatible Web Chat API proxy

Launch
31
A

Auto Browser

Give your AI agent a real browser — with a human in the loop

Launch
32
O

Openclaw.net

Self-hosted Enterprise and Personal AI + agent runtime in .NET

Launch
33
Y

Yepanywhere

Self-hosted web UI for Claude and Codex

Launch
34
D

Dodaios

Your AI assistant, built for the agentic era

Launch
35
A

Aivory

Self-hosted AI chat platform with multi-step tool calls, persistent Python…

Launch
36
G

GoGogot

Lightweight self-hosted AI agent. Open-source OpenClaw alternative in Go

Launch
37
O

Owl Browser

Self-hosted Chromium browser automation engine built for AI agents

Launch
38
H

HeliosGen

🏆 Self Hosted Gen AI desktop app

Launch
39
P

Py Idp

AI-enabled Intelligent Document Processing for Python: 12+ LLM backends

Launch
40
W

WBO

Web Whiteboard to collaborate in real-time on schemas, drawings, and notes

Launch
41
E

EpicStaff

Source-available, self-hosted platform for building AI agent flows

Launch
42
T

TurboLLM

Run any local LLM engine, auto-tuned to your GPU

Launch
43
M

MultitaskAI

Master Your AI, Maximize Your Productivity!

Launch
44
M

MindRoom

AI agents that know you and your work, in a chat app anyone can use

Launch
45
M

Marm Memory

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok

Launch
46
P

PokeDemo

Clickable product walkthroughs you export and own forever

Launch
47
R

Rag.computer

Self-hostable RAG platform - document ingestion, embedding, and vector search…

Launch
48
O

Orbit

Self-hosted AI gateway for private RAG, natural-language data access

Launch
49
O

Ollama Gui

A Web Interface for chatting with your local LLMs via the ollama API

Launch
50
M

Moyai

A self-hosted coding agent for background work

Launch

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