Question 1

How is this different from Mintlify or GitBook?

Accepted Answer

Mintlify and GitBook are great editors - but you still write the docs yourself, and their AI features just summarize prose. doc0 parses your code into a symbol graph (functions, call chains, API endpoints), generates docs from that structure, and exposes both wiki and MCP from the same source. AI tools query the graph directly, not paraphrased prose. No manual writing, no MDX files, no CI pipeline to maintain.

Question 2

How is this different from DeepWiki?

Accepted Answer

DeepWiki generates a one-time documentation snapshot. doc0 is living code context - your docs update automatically when you push code, you can edit any page without losing changes on regeneration, and you get both technical docs and user guides from the same repo. Plus private repos, team collaboration, custom domains, and an MCP server your AI tools query directly.

Question 3

How does doc0 work with Claude Code, Cursor, and Linear's Copilot?

Accepted Answer

Your AI tools stop guessing about your codebase. Every doc0 project ships with an MCP (Model Context Protocol) server, scoped by a project key. Add it to Claude Code or Cursor with one line of config; point Linear's Copilot at it from your workspace; ask the Slack bot from any channel. Each query returns grounded answers with source citations to the underlying code files. Available on every plan including Free.

Question 4

Can non-engineers (product managers, support, customer success) use this?

Accepted Answer

Yes. doc0 generates two documentation modes from the same code: a technical wiki for engineers and a user-guide wiki written for non-engineers. Both are searchable with AI chat. Product managers query it from Linear when scoping tickets; support and customer success use the Slack bot or web chat. No MDX, no markdown skills required - the interface is built for reading, not authoring.

Question 5

Does it work with private repositories?

Accepted Answer

Yes. doc0 connects via GitHub App. Your source code is analyzed in memory during generation and immediately deleted - it never touches our database. Only file hashes are stored for change detection. Source code is never used for training.

Question 6

What happens to my edits when docs regenerate?

Accepted Answer

Your manual edits are preserved. doc0 tracks provenance - which source files generated which pages. When you push code, only pages whose source files changed are regenerated. Edited pages are flagged but never overwritten.

Question 7

What languages and frameworks are supported?

Accepted Answer

doc0 works with any GitHub repository regardless of language. Code analysis uses tree-sitter AST parsing for JavaScript, TypeScript, and TSX, with file-structure analysis for all other languages. API detection supports Express, NestJS, FastAPI, Django, Spring Boot, Rails, and 10+ more frameworks.

Question 8

How does the AI chat work?

Accepted Answer

The chat retrieves the most relevant snippets from your docs and source code, then asks an LLM to compose a grounded answer with citations. Under the hood: hybrid vector + full-text search, query expansion to catch synonyms, and LLM reranking to filter noise - but you don't need to think about any of that. Every answer cites the files and symbols it's based on, so you can verify.

Question 9

How is the knowledge graph used?

Accepted Answer

doc0 doesn’t just summarize files - it maps your entire codebase into a symbol graph with call relationships, community detection, and cross-module execution flows. This powers “How It Works” pages that trace real code paths, enriches AI chat with structural context, and surfaces authorship and change frequency for every file.

Question 10

Is it free?

Accepted Answer

Free forever for public repos - 1 project with both doc modes, AI chat, unlimited MCP queries, full-text search, knowledge graph, and API detection. Pro ($19/mo) adds unlimited public projects, 5 private repos, custom domains, and export. Team ($99/mo) adds 10 included team members (+$9/mo each additional), 25 private projects, deep research, changelog, and GitHub Checks.

Your codebase, queryable from anywhere.

Claude Code, Cursor, and Linear's Copilot query your codebase via MCP.
Slack bot answers your support team.
Web wiki for everyone else.

Real docs from real repos

next.js

supabase

shadcn/ui

fumadocs

hono

drizzle

Your code, mapped

Cross-module execution flows

Live symbol graph

Grounded AI chat

From repo to live code context - three steps

Connect

Connect

Connect your repo

Generate

Generate

doc0 parses and generates

Query

Query

From every tool your team uses

Built for teams and the AI tools they use

MCP Server

llms.txt + Copy as Markdown

Source code never stored

Audit logs & access controls

Start free, scale when you need to

Free

Pro

Team

Frequently Asked Questions

Turn your repo into a
living knowledge base

Your codebase, queryable from anywhere.

Claude Code, Cursor, and Linear's Copilot query your codebase via MCP.Slack bot answers your support team.Web wiki for everyone else.

Real docs from real repos

next.js

supabase

shadcn/ui

fumadocs

hono

drizzle

Your code, mapped

Cross-module execution flows

Live symbol graph

Grounded AI chat

From repo to live code context - three steps

Connect

Connect

Connect your repo

Generate

Generate

doc0 parses and generates

Query

Query

From every tool your team uses

Built for teams and the AI tools they use

MCP Server

llms.txt + Copy as Markdown

Source code never stored

Audit logs & access controls

Start free, scale when you need to

Free

Pro

Team

Frequently Asked Questions

Turn your repo into a living knowledge base

Claude Code, Cursor, and Linear's Copilot query your codebase via MCP.
Slack bot answers your support team.
Web wiki for everyone else.

Turn your repo into a
living knowledge base