Skip to main content

{📖} Structural LLM Wiki

Structural LLM Wiki. You ask your agent one question, "How does the gateway retry?", and your agent does the rest: 1, it finds and saves the sources, a paper, code, a web page, a design doc; 2, it writes the answer, an open book in braces, every claim tied by a thread to its source; 3, it opens one pull request on project-foobar-sllmwiki.git; 4, you review and merge; 5, each release attaches the wiki as a book, in PDF, EPUB and HTML. The repository is git, which your group and their agents clone, share and grow. Answers you can check; written to teach; knowledge that compounds; stays true as sources change; reviewed like code; kept in git, shared as a book.

Claude Code plugin License: GPL v3+ Python 3.9+ Scripts Book

Your group's knowledge, researched by your coding agent, cited to the exact source, and reviewed like code.

An agent skill, packaged as a Claude Code plugin, that turns a git repository into a wiki your coding agent researches and keeps current. You ask a question. It saves the sources that answer it, verbatim copies of code, design docs, specifications, papers or web pages, and writes a narrative: an account, told in order, of what happened or how something works, every claim linked to the section of a source that supports it. Each run arrives as one pull request you review. It builds on Andrej Karpathy's LLM wiki pattern and adds what a group needs: claims you can check, review before anything lands, and a book at each release.

See one. Every narrative in the demo wiki was researched and written by an unattended run, and arrived as a pull request to review. Three recent runs, one question each:

Question Model Kind Sources saved Narrative Time Tokens Pull request
How does Raft elect a leader and keep every server's log consistent? Opus 5.5 how it works 3 (99 KB): two dissertation chapters, etcd's README 1,799 words 10 min 6.0M in, 51K out #22
What are the classic failure modes of large distributed systems, and their mitigations? Opus 5.5 survey 4 (43 KB), and 2 papers as links 1,937 words 8 min 8.7M in, 42K out #23
How does classic attention compare with paged attention? Haiku 5.5 comparison 4 (290 KB), and 1 paper as a link 982 words 7 min 4.6M in, 57K out #24

Each run reports its own time and tokens in its pull request. The tokens count the main session only, and about 98% of the input is cached. Start at the demo's index, or download its book as a PDF, EPUB or HTML file from its latest release.

Setup

You need an agent that runs Agent Skills, such as Claude Code, plus git and Python 3.9 or later; the first run installs the rest, the plugin's code (the sllmwiki package, into the plugin's own folder) and anything missing, with your package manager. gh, signed in, is recommended: it opens the pull requests (without it, the skill prints a link to open each one yourself). The wiki's CI checks and its book need the wiki hosted on GitHub.

  1. Create an empty repository (for example project-foobar-sllmwiki), clone it and start Claude Code in it.

  2. Install the plugin into it:

    claude plugin marketplace add mengjiasun1992/structural-llm-wiki --scope project
    claude plugin install sllmwiki@structural-llm-wiki --scope project
    
  3. Run /sllmwiki:init. It asks a few preferences (language, source policy, the book), lays out the wiki, installs its CI checks and makes the first commit. Rerun it after a plugin update.

  4. Ask your first questions: /sllmwiki:build "How does our gateway route requests?" "Why does it retry?"

Join a wiki: open it in Claude Code and accept the plugin it offers; its README, which init writes, says the rest. Other agents (Codex, Cursor, Copilot): npx skills add mengjiasun1992/structural-llm-wiki -g with the skills CLI and pipx install sllmwiki (the version the skill's SKILL.md names), then ask in your own words ("lint the gateway narratives").

Installing git, Python and gh
brew install git python gh                                   # macOS
winget install Git.Git Python.Python.3.13 GitHub.cli         # Windows
sudo apt-get install -y git python3 gh                       # Debian / Ubuntu
gh auth login && gh auth setup-git                           # then, everywhere

Why use it

  • Builders need to understand a system before they change it, but the why is in a design doc that drifted and a chat thread nobody can find, and an AI's answer can't say which parts it read and which it guessed.
  • Tech leads need what the group knows to outlive who knows it. Onboarding runs through the same few seniors, and nobody can say which docs are still true.
  • Researchers have more papers than time, and LLM summaries cite sections that don't say what they claim.

What the wiki does about it:

  • Every claim can be checked. Each one cites the exact section of a saved source, one click away. What no source states is marked as the narrative's own reasoning ([→]) or as a gap ([?]), never filled with a guess. Lint checks every claim and quotation against the section it cites.
  • Nothing lands unreviewed. The agent researches on its own and delivers one pull request: a checklist on top, the decisions it couldn't make, and what the run cost. Your seniors review instead of writing from scratch.
  • Knowledge compounds. One narrative per question, kept in git. A new answer builds on what the wiki already explains, and the next person who asks gets the reviewed answer.
  • Answers stay true. Each narrative records the source versions it read. When code or a doc changes, exactly the narratives that rest on it are flagged.
  • It teaches. The answer's shape fits the question, written for a reader new to the topic; describe your own kind, such as a postmortem or a ten-minute primer on a paper.
  • It knows who to ask. Each topic lists the people behind its code and docs, ranked by evidence from git history and code owners.
  • A book with every release. The whole wiki as a PDF, an EPUB or one HTML file, chapters in teaching order, diagrams and math drawn as on GitHub: an onboarding pack, current as of that day.

Every kind of question gets the shape that teaches it. What is X? In short, then rigorously, and its edge cases. How does X work? One real example, walked through with its numbers. Principles of X? The field mapped first, then each idea in brief. X or Y? Every option compared, and the rule for when each wins. What happened? The timeline, the chain of causes, and the lessons. Your own kind? A postmortem, a primer: a template you describe.

It's all plain Markdown and YAML in git: browse it on GitHub, open it in Obsidian, or use it from any agent that supports Agent Skills. Scripts do everything mechanical, so your tokens go to judgment.

Usage

Four moments, from your side. Ask anything: an answer in seconds, each claim cited, and who to ask. Grow it by asking: it researches while you're away, and you review one pull request; nothing lands till you merge. It stays true: when a source changes, exactly the answers that rest on it are flagged, and the rest stay untouched. Share it as a book: each release, such as v2026.10.24, attaches the whole wiki as a PDF to print and share, an EPUB for e-readers and phones, and one HTML file for a browser; read it offline, or hand it on.

I want to… Run
Set up a wiki (start here, in an empty repository) /sllmwiki:init
Ask the wiki: a cited answer in seconds, or a DRAFT and an offer to research it /sllmwiki:query "How does the gateway retry failed backends?"
Research questions unattended: sources saved, a cited answer each, one pull request to review /sllmwiki:build "How does the gateway route requests?" "Why does it retry?"
Publish the wiki as a book (PDF, EPUB, HTML) in a dated release /sllmwiki:release

Everything else, ask in your own words: "Lint the gateway narratives", "Who knows the gateway?", "Make a template for postmortems of our incidents", or "What can sllmwiki do?".

The manual has the rest: reviewing a run, what's in your wiki, templates, citations, books, settings, languages, Obsidian, teams, and an FAQ.

Licenses and your data

The skill is open source under the GPL 3.0 or later, and the templates it puts in your wiki and book under MIT-0, with no conditions; your wiki is yours, and each source stays its authors', kept with its URL and license, quoted briefly, never fetched past a login or paywall. Narratives are written by an LLM: every claim is cited, but review each pull request before you merge it. The plugin runs on your machine and its authors collect nothing (Privacy). The details: the manual, §12.

Design

docs/structural_llm_wiki_design.md has the architecture and the decisions behind it, and docs/book_design.md the book a release attaches. docs/skill_execution_plan.md and docs/book_execution_plan.md say how each was built.

Developing

plugin/                the plugin: instructions only
├── skills/sllmwiki/   the skill: SKILL.md, workflows/, steps/
└── commands/          Claude Code commands: init, query, build, release
src/sllmwiki/          the sllmwiki package: every command, lib/, templates/
tests/                 unit tests for the package
src/actions/           the GitHub actions a wiki's CI calls
src/tools/             development and CI tools (eval-plugin.sh, check-yaml, check-book)
evals/                 behavior evals, run through src/tools/eval-plugin.sh
docs/                  the manual, the designs, their plans, and their figures

AGENTS.md has the rules for changing this repository: tests with every logic change and coverage at 95% or above, instruction word budgets, evals for behavior changes. Run the tests, and try the plugin from a checkout:

python3 -m venv .venv && . .venv/bin/activate
python3 -m pip install -e . "coverage[toml]==7.6.10"
python3 tests/run.py --coverage
claude --plugin-dir plugin             # runs the sllmwiki on PATH: this checkout's

License

Copyright 2026 Mengjia Sun. The code is licensed under the GNU General Public License, version 3 or later; the templates in src/sllmwiki/templates/ under MIT-0. Versions up to 1.2.0 were released under Apache 2.0. See NOTICE.

Metadata

Release files for sllmwiki 1.3.0

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

Source distribution (sdist)

Source distribution for sllmwiki 1.3.0
File Size Uploaded Provenance Actions
sllmwiki-1.3.0.tar.gz 298.1 kB With provenance Details for sllmwiki-1.3.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for sllmwiki 1.3.0
File Interpreter ABI Platform Actions
sllmwiki-1.3.0-py3-none-any.whl Python 3 none any Details for sllmwiki-1.3.0-py3-none-any.whl

Total release size: 532.8 kB

Release files / sllmwiki-1.3.0.tar.gz

Download URL sllmwiki-1.3.0.tar.gz
Size 298.1 kB
Tags Source
SHA-256 checksum
How to use checksums
e138f73d3000204dc96a002cda378461dbd573712434efa7d7c5b6e43d3cf93e
BLAKE2b-256 checksum
How to use checksums
58aafad989c91fd632f1553072d3994c6b7381dad8d73009cf380512b858a672
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 7, 2026.

Transparency log

Release files / sllmwiki-1.3.0-py3-none-any.whl

Download URL sllmwiki-1.3.0-py3-none-any.whl
Size 234.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
35d658e30c87905d708abd065498ed3a530eb0d15eadbbcccb2e88fb09fb3dbf
BLAKE2b-256 checksum
How to use checksums
3ebe03708ddfaee1e733de595acdd2a8f461c56587245b810d0daed36c0e900c
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 7, 2026.

Transparency log

Security for sllmwiki 1.3.0

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 sllmwiki-1.3.0.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 7, 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.

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