llm-wiki
LLM Wiki lets you build and maintain a self-contained personal knowledge base as plain markdown, organized into immutable source material and compiled articles you own. Sources land in a `raw/` directory, you compile them into `wiki/` articles, and the system keeps everything local—readable on GitHub and openable as an Obsidian vault. Query your knowledge, ingest new sources, lint for health, audit claims against their sources, or critique reasoning, all without external servers or embeddings.
LLM Wiki helps you build and maintain a personal knowledge base as plain markdown with source tracking and Obsidian vault support.
AI-generated summary based on this skill's SKILL.md
Install
sammcj/agentic-coding/llm-wiki · repository language: HTML
git clone https://github.com/sammcj/agentic-coding
cp -r agentic-coding/Skills/llm-wiki ~/.claude/skills/llm-wikiFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I build a personal knowledge base with markdown?
LLM Wiki lets you build a personal knowledge base entirely in plain markdown, stored locally and version-controlled in git. You organize sources into a `raw/` directory and compile them into `wiki/` articles with full provenance tracking. The system keeps everything self-contained and readable in both GitHub and Obsidian, so you own all your knowledge without relying on external servers or embeddings.
How do I ingest sources into LLM Wiki and query them?
LLM Wiki accepts sources from URLs and files into your `raw/` directory, then you compile them into `wiki/` articles with proper source attribution. Once ingested, you can query your knowledge base, audit articles against their original sources, and critique the reasoning in your compiled content—all locally on your machine.
Can I organize raw sources and compiled articles separately?
Yes. LLM Wiki uses a two-layer structure: immutable source material lives in `raw/`, while your compiled, synthesized articles go into `wiki/`. This separation lets you maintain fidelity to original sources while building higher-level knowledge without mixing raw data and synthesis.
How does LLM Wiki handle stale or outdated knowledge?
LLM Wiki uses supersession instead of deletion—you mark knowledge as stale, record gaps, and cascade updates through your wiki without erasing history. This approach keeps your knowledge base auditable and lets you track how your understanding evolved over time.
Can I lint my LLM Wiki knowledge base for consistency?
Yes. LLM Wiki includes tools to query, audit, and critique wiki content for consistency and fidelity to sources. You can lint your knowledge base for health, check articles against their provenance, and identify reasoning gaps—all without leaving your local, version-controlled markdown vault.
Is LLM Wiki compatible with Obsidian and git?
LLM Wiki is designed to be readable in git and openable as an Obsidian vault. Your entire knowledge base stays local and plain-text, so you can version-control it, browse it on GitHub, and edit it in Obsidian or any markdown editor—no proprietary formats or lock-in.
SKILL.md
rendered from the published skill — quoted content, verbatim
LLM Wiki
Build and maintain a personal knowledge base as plain markdown. You manage two directories: raw/ (immutable source material) and wiki/ (compiled knowledge you own). Sources land in raw/, you compile them into wiki/ articles, and the wiki compounds over time. Everything is local markdown with YAML frontmatter, readable on GitHub and openable as an Obsidian vault. No servers, no databases, no embeddings.
Core idea (Karpathy): the LLM writes and maintains the wiki; the human chooses sources and asks questions. Knowledge is compiled once at ingest and kept current, not re-derived on every query. That is the difference from RAG, which
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 15 files
Skills/llm-wiki/.gitignore
Skills/llm-wiki/CHANGELOG.md
Skills/llm-wiki/CLAUDE.md
Skills/llm-wiki/LICENSE
Skills/llm-wiki/README.md
Skills/llm-wiki/SKILL.md
Skills/llm-wiki/examples/CLAUDE.md
Skills/llm-wiki/examples/README.md
Skills/llm-wiki/examples/SKILL.md
Skills/llm-wiki/examples/local/prep/2026-06-04-attention-talk-prep.md
Skills/llm-wiki/examples/raw/machine-learning/2017-06-12-attention-is-all-you-need.md
Skills/llm-wiki/examples/raw/machine-learning/2022-05-27-flashattention.md
Skills/llm-wiki/examples/wiki/README.md
Skills/llm-wiki/examples/wiki/gaps.md
Skills/llm-wiki/examples/wiki/index.md