Skip to content
Live

Draw the architecture.
Keep the code honest.

Graphlit turns a whiteboard sketch into a typed architecture graph, builds a working app from it, and verifies on every commit that the code still matches the drawing.

curl -fsSL https://graphlit.co/install.sh | sh

Run it from anywhere. It asks which folder to turn into a project. Already installed? Run graph setup inside the folder you want.

bash · zsh · sh · dash · fish · Git Bash · no sudo, nothing outside your home directory · read the script first

Free to start · your code stays yours · export any time

checkout-flow · board
An empty board
LoginDashboardPaymentsSuccessLoginscreenapp/login/page.tsxDashboardscreenapp/dashboard/page.tsxPaymentsapi…p/api/payments/route.tsSuccessscreenapp/success/page.tsxAuthservice · inferredlib/auth.tsUsertable · inferredprisma/schema.prisma

No prompt. No template. No prose.

The problem

Everyone ships the ceiling. Nobody ships the floor.

  • A thousand-line prompt

    Boxes and arrows

  • Code with no link to the ask

    Every node → a real file, hashed

  • Your first hand-edit ends it

    A hand-edit becomes a decision

  • Greenfield only

    Import what you already have

The part nobody else has

Three weeks later, is the drawing still true?

Press the button. It runs.

  • In syncstill hashes to what we built

  • Changedhand-edited — accept or rebuild

  • Gonethe file is no longer there

  • Unbuiltdrawn, never built

checkout-flow · sync
GraphFlowsTasksHealthSync

Five nodes claim a file in this repo.

Press Check sync to hash every one of them against the code that is actually on disk right now.

Inside the product

Five surfaces, one graph underneath

checkout-flow · graph
GraphFlowsTasksHealthSecurity

Typed nodes and edges, laid out automatically. Select anything to see where it lives.

~/work/acme-store · import

You do not have to start from a drawing.

Point it at a repository that already exists (a local folder, a git URL, or an upload) and the same graph comes out the other side.

Start where you are

Already have a codebase? Better.

Most tools here need you to start from nothing.

A map that's derived

not drawn in 2024

Rules you can enforce

not a wiki page

Change with a blast radius

scoped to real files

An audit that starts focused

risk by architecture

Under the hood

Mostly not a model, on purpose

Two stages need a model. The other five don't.

One task, end to endReader4 of 7 stages run no model
Reader

Sketch → shapes

deterministic

Intent

Shapes → typed nodes

model

Planner

Infer what wasn't drawn

model

Task engine

Graph → ordered work

deterministic

Executor

One task, then stop

model

Gate

Green or reverted

deterministic

Sync

Drawing still true?

deterministic

6 shapes, 5 arrows, 6 labels recovered from the board

Watch it

Two minutes, start to finish

checkout-flow · a full run1/6 · You draw
LoginDashboardPaymentsSuccess

Four boxes, three arrows. No prompt.

0:00 / 0:20
Live — not a recording
Every stage of the loop, drawn to built, in the order it happens.
  1. 0:00

    You draw

  2. 0:03

    It types the graph

  3. 0:07

    It plans the work

  4. 0:10

    It builds one task

  5. 0:14

    The gate runs

  6. 0:17

    It checks the drawing

Everything in the box

Ten capabilities, one underlying idea

Proof, not a promise

We build Graphlit with Graphlit

A tool that keeps architecture honest should survive being pointed at itself. Ours is the first codebase it had to.

0
findings against our own code
One is enough to fail the build.
4,876
tests on every change
Re-run it yourself.
Every
claim here is a command
If we can't re-run it, it isn't printed.
227
security rules
platform-keyed
4,876
automated tests
on every change
0
findings on our own code
enforced in CI
0
prose required
boxes and arrows

Questions

Short answers

Need a longer one? Ask.

Is this another prompt-to-app tool?

No — those stop caring about your code the moment it's generated; this keeps checking it against the drawing.

Do I have to draw? I'm not a designer.

Boxes and arrows, with your finger if you like — or import a repo and never draw anything.

Does it work on my existing codebase?

That's the case it's strongest at.

What happens when the AI writes something wrong?

The task is reverted with the real error — we bound the damage, we don't pretend it can't happen.

Who owns the code?

You do — export it any time, including before you ever pay us.

Do you train on my code?

No, and most of the product never sends it to a model at all.

Can I use my own model provider?

Yes, on any plan — an Anthropic key, an Amazon Bedrock role, OpenRouter, or any endpoint that speaks the OpenAI protocol, with your own address and model names, and yours answers before ours does.

What languages?

Mixed Python and TypeScript today — Next.js, FastAPI, Flask, Prisma, SQLAlchemy, raw SQL.

When can I use it?

Nothing to wait for — create an account and it works straight away. Existing codebases are where it earns its keep fastest.

Point it at something real

Import a repository you already have and see the architecture it derives — and where the code has already drifted from it.

Free to start. Import a repo and the graph is there in minutes.