Skip to main content

Turn any folder into a queryable knowledge graph. Inspired by Andrej Karpathy's LLM Wiki concept.

Project description

my-llm-wiki logo

my-llm-wiki

Turn any folder of code, docs, papers, or images into a queryable knowledge graph.

Documentation · PyPI · Issues


Inspired by Andrej Karpathy's LLM Wiki concept: drop raw files → compile once → query forever.

Install

pip install my-llm-wiki
pip install my-llm-wiki[all]   # PDF + .docx/.xlsx + Leiden clustering

Usage

llm-wiki .                          # build graph → wiki-out/
llm-wiki query gods                 # most connected nodes
llm-wiki query search <term>        # keyword search
llm-wiki query neighbors <label>    # direct connections
llm-wiki query path <A> <B>         # shortest path
llm-wiki watch .                    # auto-rebuild on changes
llm-wiki add <url>                  # ingest URL as markdown

Claude Code Skill

For deep extraction of DOCX, scanned PDFs, and images via agent mode:

mkdir -p ~/.claude/skills/my-llm-wiki
cp "$(python -c 'import my_llm_wiki; print(my_llm_wiki.__path__[0])')/SKILL.md" ~/.claude/skills/my-llm-wiki/

Then /wiki . in Claude Code runs structural + semantic extraction.

Docs

Full documentation at phuc-nt.github.io/my-llm-wiki

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

my_llm_wiki-0.2.1.tar.gz (61.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

my_llm_wiki-0.2.1-py3-none-any.whl (77.9 kB view details)

Uploaded Python 3

File details

Details for the file my_llm_wiki-0.2.1.tar.gz.

File metadata

  • Download URL: my_llm_wiki-0.2.1.tar.gz
  • Upload date:
  • Size: 61.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for my_llm_wiki-0.2.1.tar.gz
Algorithm Hash digest
SHA256 ad19ff83e777a4768fe70d0b71cfabbfdc513cba2ff78c2eeed6fcad0052cc1f
MD5 45280c40cf9a22e1ae776bb11af622a2
BLAKE2b-256 0d0d5396fc97755012595c9ed8f058fa8de8796a8c9ae48642094381c72a8e2a

See more details on using hashes here.

File details

Details for the file my_llm_wiki-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: my_llm_wiki-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 77.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for my_llm_wiki-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 5e8ab88fcf1c21d2f6ee57fd99501b5d4225bc592e476456b50022de740f7449
MD5 fa8027bcabf0c6118a1dc439fea21e25
BLAKE2b-256 42c5add6fbd6d21cf84a86f5bf0f14fe194f0ac1b15a27b87db6b2f6e061f9fa

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page