This is experimental software and is not fully tested. It is developed in the open and there is plenty still to do — read the code, run it yourself, and judge it on what it actually produces. Todo — the road to 1.0.0 → Source on GitHub →
Describe your business process in plain English. AppWithAI drives an intelligent multi-agent pipeline — from domain analysis and ERD design to human-in-the-loop review and complete code generation — producing a fully functional, deployable application.
Neither player is embedded until you press it — this page asks YouTube for nothing until you ask it to. What this site collects →
Every organization has unique business processes. Traditional custom application development is slow, expensive, and produces systems that resist change.
Time-to-Value: 6–18 months
Total Cost: Six figures and above
Process: Requirements gathering → Data modeling → Form development → Business rules → Workflow configuration → Integration and testing → Ongoing modification cycles
Every change requires developers, QA cycles, and deployment windows.
Time-to-Value: 1–3 weeks
Total Cost: Significantly reduced — no large development team required
Process: Describe your domain → AI analyzes and models → Human reviews and approves → Production-ready application is generated
Administrators update business rules, forms, and workflows in minutes through the admin interface.
A small software company can hold outstanding domain knowledge and still be unable to staff an architect, a database specialist, a UI designer, a security reviewer and an operations engineer. The decisions those people would make still get made — just by whoever is available.
AppWithAI moves that expertise into the platform, so a ten-person team can build with the engineering consistency of a much larger one.
Read why AppWithAI exists →A complete platform for generating enterprise-grade business applications — from intelligent data modeling through to production deployment.
Describe your business domain and let AI extract entities, relationships, and build a complete ERD automatically — reviewed and approved by you before any code is written.
Generate data-driven forms that mirror real-world business documents, with auto-validation, calculated fields, conditional visibility, and runtime customization.
Multi-level approval workflows with conditional routing, escalation chains, delegation, SLA enforcement, and tamper-proof audit trails.
Define complex business logic using visual decision flowcharts powered by GoRules Zen Engine. AI translates rules into executable TypeScript code with full lifecycle hook support.
Table-level, field-level, and row-level access control with complete audit trails. RBAC is generated automatically for every application entity.
Embedded conversational AI assistant powered by CopilotKit provides real-time guidance, natural language data queries, and in-application help for end users.
A sophisticated multi-agent AI pipeline, orchestrated by Mastra.ai, transforms your business description into deployable software.
Write your business domain in plain English. No technical knowledge or coding required.
The Domain Analysis Agent — powered by Claude, OpenAI, or a local Ollama model of your choice — extracts core entities, attributes, and relationships from your description.
You review and approve the AI-generated data model in the visual ERD designer. Only after your explicit approval does the system proceed.
The Mermaid Agent produces a complete Entity Relationship Diagram, which feeds the Code Generation Engine to produce the full application.
Your application is ready to deploy on any cloud provider or on-premise. Customize forms, rules, and workflows through the admin interface without touching code.
You do not need an account, an install, a sales call, or our permission. Describe your business to an AI you already use, bring back one file, and watch a working application start in this browser. Ten minutes, start to finish.
Not one sentence. Write what you would tell a new hire on their first day: what you sell or service, every kind of record you keep, who touches each one, the states things move through, what needs approving and by whom, and what happens when a step fails.
The thinner the description, the thinner the application. This is the step that decides the result.
Give the model our machine-readable specification along with your description. It contains the authoring protocol: enhance the brief into a full entity model, workflows and business rules; write the model file; then validate it against our published checker before handing anything over.
You get back a single .mmd file — the model itself, not a document describing it — plus the specification it inferred so you can correct what it guessed.
Upload that file and watch it become a complete application — PostgreSQL compiled to WebAssembly, a real API, a real interface, business rules and workflows running. No install. No signup. Nothing leaves your machine.
Your model is parsed in the tab, the app is assembled in the tab, and its database lives in the tab.
Replace only the description. Everything else tells the model where the specification lives and what it must do before it answers you.
Read https://appwithai.org/llms-full.txt in full, and follow section 1 — the authoring protocol — exactly.
My business:
[Describe it here. What you sell or service. Every kind of record you keep and how they relate. Who does what. The states each record moves through. What has to be approved, and by whom. What happens when a step fails.]
Deliver exactly one file I can download: <business-name>.mmd. It must open on a %% line with %%meta name: before the first diagram, and every line in it must be Mermaid or an EML %% directive — no Markdown, no headings, no prose. A document that describes the model is not the model; the checker scores that EML004.
Send no other file — no specification document, no report, no README. If you can only answer with a document, put the entire model in the first fenced mermaid block of that document, before any prose.
Then, in your reply text: the enhanced specification you inferred, the checker result with its counts, and anything you assumed.
Upload the .mmd and press Generate, then Run. The first time PostgreSQL loads it takes a few seconds; after that it is instant.
Got a report instead of a file? Some models can only answer with a document. Copy its mermaid block into the checker page, check it, and download it as a .mmd from there.
Not ready to write your own? Run the seventeen-entity CRM the guide builds — same page, one click, no file needed.
Want the longer version — what the model file actually contains, and how to check it? The Try It Yourself page walks all of it.
Building professional or enterprise software rather than a first model? Point the same prompt at the detailed specification and follow its section 10 — a phased walkthrough with approval gates instead of one pass. The prompt for it is here.
Whichever prompt you use, you get a Mermaid file back — and Mermaid draws only its entity diagram. The model viewer draws the rest: the business rules, the state machines, the multi-step processes and who can see what.
AppWithAI is released under the Apache License 2.0, one of the most permissive and enterprise-friendly open source licenses available.
Use AppWithAI in any project — commercial or personal — without licensing fees or royalties.
Fork the repository, extend the generator, customize templates, and contribute improvements back to the community.
Distribute modified versions of AppWithAI and generated applications with no vendor lock-in, ever.
The Apache License 2.0 grants you a perpetual, worldwide, royalty-free license to reproduce, prepare derivative works, publicly display, sublicense, and distribute the software. It includes an explicit patent grant, protecting contributors and users alike.
AppWithAI — copyright 2026 AppWithAI Contributors. All generated code belongs entirely to you.
AppWithAI generates applications across a wide range of business functions and industries.
Purchase Orders, Invoice Processing, Expense Claims, Budget Requests, Cost Center Management
Leave Requests, Onboarding Workflows, Performance Reviews, Training Records, Offboarding
Work Orders, Maintenance Requests, Inventory Management, Asset Tracking, Field Service
Quotations, Customer Contracts, Commission Calculations, Opportunity Tracking, Sales Reports
Vendor Registration, RFQ Management, Contract Lifecycle Management, Vendor Scorecards
Policy Acknowledgements, Incident Reports, Audit Findings, Risk Registers, Control Testing
Most software demos are a recording, a sandbox someone else reset, or a calendar invite. This one is the real generated application, compiled and started inside your own browser tab while you watch.
Every entity, rule, workflow, screen and permission comes out of one Mermaid model file. Nothing on the screen was hand-written — including the help text.
The generated application runs in your browser — no server, no account, no install
The model is parsed in the tab, the app is assembled in the tab, and its database lives in the tab
Or upload your own model and run that instead
AppWithAI generates equivalent applications for any business domain — the CRM is simply the one we walk through end to end.
Request a Demo for Your DomainFollow a single model file all the way to a running enterprise CRM — data model, business rules, workflows, generation, and the finished application. Every screenshot in the guide comes from the application it builds.
The guide starts with an empty file and ends with a CRM covering the whole commercial lifecycle — marketing captures a lead, sales converts it into an account with a contact and an opportunity, the deal is quoted and contracted, and support handles cases against the account afterwards.
Nothing in the finished application is hand-written. The data model, the decision logic, the status lifecycles and the multi-entity processes all come out of the same document, and the document stays readable as a diagram.
Entities, attribute types, foreign keys, relationships, enums, indexes and dashboard grouping.
Decision flows that score, route and gate — evaluated inside the transaction that saves a record.
Status lifecycles, lifecycle hooks, and multi-step sagas that create and update across entities.
Windows, tabs and fields, the rule and workflow editors, the audit log and per-screen help.
Qualify a lead and follow the rule, the action, the saga and the three rows it creates.
Generate the application from the model and run it in the page — PostgreSQL in WebAssembly, no server, no install.
Watch AppWithAI generate a complete business application from your description — live, in your meeting, in under 30 minutes.