Skip to main content
DeepDoc

DeepDoc

Documentation that keeps pace with your codebase.

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

PyPI version Python versions License: MIT

Docs · Try it in the browser · Changelog


Quick start

You need Python 3.10+ and Node.js 18+.

pip install deepdoc
cd your-project
deepdoc init --provider anthropic
export ANTHROPIC_API_KEY=sk-ant-...
deepdoc generate
deepdoc serve          # http://localhost:3000

No install? cloud.deepdoc.tech runs the same generator: sign in with GitHub, pick a repository (private ones too), get a docs site. Sites are private by default.

What you get

  • Docs 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 optional chatbot ships with the site. Every answer points to a file path and line range, in a fast mode or a deeper research mode.
  • Updates that touch only what changed. deepdoc update diffs against the last synced commit and regenerates only the affected pages.
  • Theming that costs nothing. Colours, logo, fonts, layout and navigation are re-applied from your saved plan on deepdoc serve, with no regeneration and no LLM calls.
  • A quality gate. deepdoc deploy refuses to publish pages that failed validation.

Commands

Command What it does Calls an LLM
deepdoc init Write .deepdoc.yaml No
deepdoc generate Scan, plan and write the docs Yes
deepdoc update Refresh docs after code changes Yes, for changed pages
deepdoc serve Preview locally with live reload No
deepdoc deploy Build a static site into deepdoc-site/out/ No
deepdoc status Show what exists and what is stale No
deepdoc config show|set Read or write config values No
deepdoc performance Timing and token metrics for recent runs No
deepdoc clean Remove what DeepDoc created No
deepdoc benchmark Score planner quality Depends

Every flag is documented in Commands.

Providers

--provider accepts anthropic, openai, azure, ollama, or any LiteLLM alias such as gemini or groq. Ollama runs fully local with no API key. See Providers for each provider's key, model and Azure requirements.

Supported stacks

Endpoint, runtime and call-graph analysis cover:

Language Frameworks
Python Django, Django REST Framework, FastAPI, Falcon
JavaScript / TypeScript Express, Fastify, NestJS
PHP Laravel
Go net/http and common routers
Vue Components and symbols

Other languages may parse, but are not fully supported. DeepDoc prints a warning when it finds source it cannot analyse.

Chatbot

Off by default. Enable it with deepdoc init --with-chatbot or deepdoc config set chatbot.enabled true, install the extra, and deepdoc serve starts the backend next to the site:

pip install "deepdoc[chatbot]"

Embeddings default to a local fastembed model, so one API key is usually enough. See Chatbot for modes, models and deployment.

Keep docs current in CI

- uses: actions/checkout@v4
  with:
    fetch-depth: 0          # update needs history to diff against
- run: pip install deepdoc
- run: deepdoc update --strict-quality
  env:
    ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

examples/deepdoc-refresh.yml is a complete workflow. Commit .deepdoc.yaml and .deepdoc/: the saved plan is what makes theming and updates cheap.

Repository layout

Path What it is
deepdoc/ The Python package: CLI, scanner, planner, generator, chatbot and site builder
web/ deepdoc.tech, its product docs and the hosted app, one Astro project
vscode-extension/ Explain selected code in Fast or Deep mode and insert comments inline
hosted-runner/ The container that generates docs for DeepDoc Cloud
tests/ The pytest suite: python3 -m pytest -q

Contributing

See CONTRIBUTING.md for local setup, code style, testing and the release flow. Agents working in this repository should read AGENTS.md.

License

MIT

Metadata

Release files for deepdoc 0.6.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for deepdoc 0.6.3
File Size Uploaded Provenance Actions
deepdoc-0.6.3.tar.gz 826.7 kB With provenance Details for deepdoc-0.6.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for deepdoc 0.6.3
File Interpreter ABI Platform Actions
deepdoc-0.6.3-py3-none-any.whl Python 3 none any Details for deepdoc-0.6.3-py3-none-any.whl

Total release size: 1.5 MB

Release files / deepdoc-0.6.3.tar.gz

Download URL deepdoc-0.6.3.tar.gz
Size 826.7 kB
Tags Source
SHA-256 checksum
How to use checksums
f7a2e24074ae4eae2452d2a22dfd05a2b34b68be728f570eeb8bf2826b9de5a2
BLAKE2b-256 checksum
How to use checksums
bbdbe0edf9cd66de9cfa93e0ea74673e78a4344da5891965a2ad2fb622b3dd88
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 12, 2026.

Transparency log

Release files / deepdoc-0.6.3-py3-none-any.whl

Download URL deepdoc-0.6.3-py3-none-any.whl
Size 683.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d21c53d77dbb9c6d8763ab1bb4644c2c60c525f4778157fce3ce43a59ca2b29e
BLAKE2b-256 checksum
How to use checksums
6d8527969bcdcced86227fadba085ad523a6f3d7345eb0028a6cc7f6f3a170a0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 12, 2026.

Transparency log

Security for deepdoc 0.6.3

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for deepdoc-0.6.3.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 12, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.6.3 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page