llm-wiki
llm-wiki lets you construct and maintain a compounding knowledge base as organized markdown files, with the agent handling summarization, cross-referencing, and consistency checks while you direct curation. Unlike RAG systems that rediscover knowledge per query, your wiki compiles once and stays current, with contradictions flagged and synthesis reflecting all ingested material.
llm-wiki helps you build a persistent, interlinked markdown knowledge base with agent-assisted curation and automatic cross-referencing.
AI-generated summary based on this skill's SKILL.md
Install
NousResearch/hermes-agent/llm-wiki · repository language: Python
git clone https://github.com/NousResearch/hermes-agent
cp -r hermes-agent/skills/research/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 markdown knowledge base with llm-wiki?
llm-wiki lets you construct a persistent markdown knowledge base by ingesting sources—research papers, articles, notes—and having the agent synthesize them into organized wiki pages. You direct curation while llm-wiki handles summarization, cross-referencing between pages, and linking related concepts. Unlike RAG systems that rediscover knowledge per query, your wiki compiles once and stays current as you add material.
Can llm-wiki ingest sources into my wiki?
Yes. llm-wiki ingests sources and synthesizes them into organized wiki pages with cross-references and provenance tracking. You feed it research papers, articles, or notes, and the agent creates or updates markdown pages that reflect all ingested material, building a compounding knowledge base that grows with your research.
How do I query my existing knowledge base with llm-wiki?
llm-wiki lets you query your compiled knowledge with cross-references and provenance information built in. Because your wiki is persistent markdown files rather than ephemeral retrieval results, queries draw from a stable, curated foundation that reflects all prior synthesis work, not just the most recent ingestion.
Does llm-wiki audit wiki health and broken links?
Yes. llm-wiki includes auditing capabilities to check wiki health: it detects broken links, identifies orphaned pages, flags contradictions between pages, and surfaces stale content. This helps you maintain consistency and catch gaps in your knowledge base as it grows.
Can I integrate llm-wiki with Obsidian?
llm-wiki supports Obsidian integration for browsing and syncing your markdown wiki. This lets you use Obsidian's graph view and note-linking features alongside llm-wiki's synthesis and auditing, creating a seamless workflow between agent-driven curation and manual exploration.
What license does llm-wiki use?
llm-wiki is released under the MIT license, allowing free use, modification, and distribution for personal and commercial projects.
SKILL.md
rendered from the published skill — quoted content, verbatim
Karpathy's LLM Wiki
Build and maintain a persistent, compounding knowledge base as interlinked markdown files. Based on Andrej Karpathy's LLM Wiki pattern.
Unlike traditional RAG (which rediscovers knowledge from scratch per query), the wiki compiles knowledge once and keeps it current. Cross-references are already there. Contradictions have already been flagged. Synthesis reflects everything ingested.
Division of labor: The human curates sources and directs analysis. The agent summarizes, cross-references, files, and maintains consistency.
When This Skill Activates
Use this skill when the user: - Asks to create, build, or start a wiki or knowledge base - Asks to ingest, add, or process a source into their wiki - Asks a question and an existing wiki is present at the
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
skills/research/llm-wiki/SKILL.md