Launching today
LLM Wiki Tools
A compounding wiki your LLM builds and maintains.
2 followers
A compounding wiki your LLM builds and maintains.
2 followers
LLM Wiki Tools turns your documents into a living wiki maintained by Claude. Upload PDFs, office docs, notes, and web articles, connect Claude through MCP, and let it compile your sources into cited Markdown pages, concept pages, entity pages, tables, diagrams, and cross-references.
Hi Product Hunt,
I built LLM Wiki Tools because I kept running into the same problem with AI document workflows: the answer might be useful, but the work disappears into chat history.
Most file chat and RAG products retrieve chunks, answer the current question, and then start over next time. That is helpful, but it does not feel like building knowledge.
LLM Wiki Tools takes a different approach. You upload your sources, connect Claude through MCP, and let Claude build a persistent wiki on top of your documents. The raw sources stay immutable. The wiki layer becomes the place where Claude writes summaries, entity pages, concept pages, comparison tables, citations, cross-references, and notes about contradictions.
The goal is simple: AI-assisted reading should compound.
What you can do with it:
- Upload papers and ask Claude to build a cited research overview.
- Turn course readings into a study wiki with a glossary and concept index.
- Compare reports and save the result as a source-grounded table.
- Ask Claude to lint the wiki for contradictions, stale claims, orphan pages, and missing citations.
- Connect Claude, Cursor, custom agents, or scripts through MCP/API keys.
Every plan includes the core product: OCR, citations, full-text search, semantic search, and MCP access. Paid tiers mainly increase capacity.
I would especially love feedback from researchers, students, writers, analysts, and builders using Claude or MCP in serious document-heavy workflows.
Thanks for checking it out.