Open source · MIT · Not backed by YC

Documentationthatkeepspacewithyourcodebase.

DeepDoc reads your repository and writes a docs site with a chatbot that cites real files, then regenerates only the pages your commits touch.

Generate docs for a repo

Python 3.10+ · Bring your own model · View on GitHub

A real run on Pranav322/youtube-notes · 6m 12s, shown in 42 seconds

Music: “Aitech” by Kevin MacLeod (incompetech.com), licensed under CC BY 3.0.

What it does

One command. A docs site your team won’t ignore.

Organised the way readers look

Architecture, endpoints, integrations and schemas grouped by domain, not one noisy page per file.

Answers that cite real files

An assistant ships with the site. Every answer points to a file path and line range in your source.

Updates touch only what changed

After a commit, only the affected pages regenerate.

Restyle it for free

Colours, logo and navigation re-apply from the saved plan. No LLM calls.

Pipeline

Five phases. No magic.

Every page is grounded in scanned evidence and checked against the source before the site builds. Only two phases spend tokens.

01

Scan

Parses your source locally and maps what is there: routes, models, background jobs, integrations and OpenAPI specs.

No LLM
How it works

Get started

Two ways in.

In the browser

Sign in with GitHub, pick a repository (private ones too) and get a docs site at a stable address. Private by default.

Open DeepDoc Cloud

In your terminal

Install the CLI, bring your own model, and keep everything on your machine. Works with a local model too.

Read the quickstart

Works with

The stacks your backend already runs on.

  • Python
  • Django
  • Django REST Framework
  • FastAPI
  • Falcon
  • Go
  • net/http
  • TypeScript
  • JavaScript
  • Express
  • Fastify
  • NestJS
  • PHP
  • Laravel
  • Vue
  • OpenAPI

Endpoint, runtime and call-graph analysis cover these stacks. Other languages may parse, but are not fully supported.

Your codebase already tells a story. Let it.