llm-wiki-v2
Turn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW: 99.5% right note read vs
What is llm-wiki-v2?
Turn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW: 99.5% right note read vs 79%, 1.6× faster ingest, 63% fewer LLM tokens, no scaling limit.
Overview of llm-wiki-v2
What it is
LLM Wiki v2 is a tool that turns your documents into a Markdown wiki you can read. It answers questions with citations to the notes it used. It works with any LLM provider, including OpenRouter, OpenAI, Gemini, Ollama (free and local), or any OpenAI-compatible server. By default it uses CROW mode, where a small classifier decides where things go, keeping the wiki fast and cheap as it grows.
Key features
- Add documents: drop text, Markdown, PDF, Word, PowerPoint, Excel, or OpenDocument files. Each file lands in the right folder, merged with existing knowledge. Spreadsheets give one note per sheet.
- Ask questions: type a question; the answer cites the notes it used. Click a citation to read the note.
- Give Claude a memory: use the Memory feature to connect Claude Code, Codex, or any MCP client. The wiki becomes long-term memory, with tools to recall, remember, and read notes.
- See the brain: a live map of folders, notes, and links.
- Delete: hover a note or folder in the sidebar and press the bin, or use Delete note at the foot of a note. Empty the wiki on the home page to start over.
- Move and describe: Move at the foot of a note files it in another folder; links follow. The pencil beside a folder edits its description, which the librarian routes by.
- Keep your files: plain Markdown in ~/llm-wiki, editable in any editor and storable in git.
Use cases
- Turn any collection of documents into a readable, searchable wiki that answers questions with citations.
- Provide long-term memory for AI coding assistants like Claude Code or Codex via the MCP protocol.
- Run entirely locally with Ollama for free, private document management.
Getting started
Install with Python 3.11 or later (preferably in a virtual environment): bash pip install llmwiki2 Or use uv (which also fetches Python): bash uv tool install llmwiki2 Start the wiki: bash llmwiki2 Your browser opens. Pick a provider, paste its key, press Test connection, then Save and start. To try a demo without a key: bash llmwiki2 demo
License and pricing
The project is open source under the AGPL-3.0 license. It is free to use.
Based on the project's public README and repository metadata.