An AI that reads your code

Creating docs, likeyour code.

Drop a GitHub URL or describe your project. Caveman scans your file tree, maps dependencies, and writes a README that matches what you actually built.

scroll

Trusted by teams building on the world's top platforms

What we do

We don't template. We read your code.

UI/UX design isn't just about aesthetics. Neither is documentation - it's about making interactions smooth and workflows clear. Caveman turns your codebase into a polished, accurate document in seconds.

Deep scanning

Reads your actual source

Caveman walks your file tree, resolves imports, and detects your framework, language, and architecture - no guessing, no generic filler.

Adaptive sections

Sections that match your stack

Installation, usage, API reference, environment variables - only included when your project actually has them.

No lock-in - export markdown and take it anywhere.
0+

README sections

0

writing tones

0

documentation depths

0s

target generation window

How it works

Three cave-simple steps

From URL to polished README in under 90 seconds.

hand-drawn cheerful character face illustration
01

Sign in & start

Continue with Google to open the README generator.

Your account tracks the early-access generation limit. No credit card is needed.

hand-drawn person demonstrating an integration
02

Connect your project

Paste a GitHub URL or type a quick description. Zero setup.

Public repositories work by default. Private scans require a future user-scoped GitHub authorization flow.

hand-drawn werewolf character illustration
03

Generate & refine

Caveman scans the project and writes a grounded README.

Preview, edit, copy, or download the generated Markdown before you ship it.

Features

Every feature, no filler

Template generators fill in your project name. Caveman reads your entire codebase.

hand-drawn person debugging an API
Core

Deep code analysis

Reads your actual source files - entry points, components, APIs, and config. Writes docs that match your real codebase.

hand-drawn person configuring an API
Detection

Stack auto-detection

Detects React, Next.js, Tailwind, Prisma, tRPC, Express, Django, and more from your dependencies and file tree.

hand-drawn person configuring a server
CLI

Package manager aware

Reads lockfiles to generate accurate install commands - npm, pnpm, yarn, bun. Even handles monorepo workspaces.

hand-drawn person designing a data schema
Structure

Architecture mapping

Identifies your project structure, component hierarchy, API routes, and data models. Generates accurate architecture diagrams.

hand-drawn expressive face for quality feedback
Quality

Health scoring

Built-in README quality checker scores your docs against 11 criteria. Missing sections? It auto-generates them.

hand-drawn face behind a book illustration
Flexible

17+ customizable sections

Installation, Usage, API Docs, Contributing, Features, Architecture, Testing, Deployment - toggle any combination.

hand-drawn expressive face for tone and style
Custom

Tone & style control

Switch between Technical, Friendly, or Enterprise tone. Choose Minimal, Standard, or Comprehensive depth. One click.

hand-drawn person deploying a release
Speed

Under 90 seconds

Designed to turn a repository or project description into a polished README in under 90 seconds, with preview, editing, copy, and download.

hand-drawn person building a dashboard
Depth

GitHub deep scan

Traverses up to 3 directory levels and selects a bounded set of high-signal source files - components, API routes, config, and schemas - before writing.

Recent work

READMEs that actually look good

No template filler. Every section is written from your actual source code.

next-forge/README.mdTypeScriptMIT
## Installation

```bash
npm install next-forge
```

## Usage

```tsx
import { ForgeProvider, useForge } from "next-forge";

function App() {
  const { data, isLoading } = useForge("/api/build");
  return <div>{isLoading ? "Building..." : data}</div>;
}
```
prisma-orm-kit/README.mdTypeScriptApache-2.0
## Tech Stack

- **Runtime:** Node.js 20+, Bun 1.0+
- **Framework:** Next.js 15 with App Router
- **Database:** PostgreSQL 16 via Prisma ORM
- **Auth:** NextAuth v5 with Google provider
py-data-pipeline/README.mdPythonMIT
## API Reference

### `process_pipeline(data: dict) -> dict`

Processes raw data through the transformation pipeline.

| Parameter | Type | Description |
|-----------|------|-------------|
| data | dict | Input data with `source` and `config` keys |
| normalize | bool | Whether to normalize output (default: True) |
hand-drawn person demonstrating a website

What you get

Production-ready. Every time.

README.md - CavemanInteractive example · LaunchKit
Explore the output
LaunchKit

LaunchKit

A typed starter for shipping production-ready web apps with auth, billing, and background jobs.

MITTypeScriptReactNext.jsPrisma

LaunchKit gives teams a typed foundation for building and shipping web products without repeating the same setup work.

Auth includedAPI-firstType-safeDeploy-ready

Comparison

Why template generators fall short

Feature
CavemanOthers
Reads actual source code
Detects frameworks & stack
Writes production READMEs
Deep semantic scanning
Custom section selection
Package manager detection

Testimonials

Our clients say it best

"I spent more time writing READMEs than code. Caveman dropped that to zero. It actually reads my components and writes docs that match what I built."

Alex Chen

Founder, Finch

"The deep scan is what sold me. It found my tRPC router, my Prisma schema, and my Tailwind config - the README it wrote was better than what I would have written."

Jordan Taylor

Engineer, Rivet

"We were using a template generator before. This is different - it understands the architecture, not just the name of the project. Night and day."

Samir Patel

Lead Dev, Mantle

FAQ

Questions? We got answers.

Yes. It fetches your file tree from GitHub, identifies entry points, and sends a bounded set of high-signal source snippets to the AI. It reads your components, APIs, config files, and dependencies to understand what you built.

Let's talk.

One click. Your repo scanned. A README that describes what you actually built - not what a template thinks you built.

No credit cardFree during early accessGoogle sign-in only
Caveman is an AI README generator that turns any GitHub repository into production-ready documentation. Unlike template generators that only fill in a project name, Caveman deep-scans your actual source code - entry points, dependencies, API routes, and config files - to detect your framework, package manager, and architecture, then writes every section from real context. It supports 17+ customizable sections, technical to friendly tones, and is designed to finish within the configured generation window. Caveman is free during early access and requires a Google sign-in for generation. Public repositories work by default. Private repository scanning is not enabled because repository access must be bound to the requesting GitHub user.