llm-wiki-v2
by crow-hq
LLM Wiki v2 turns your documents into a wiki of Markdown notes and answers questions about them, citing the notes it used. It runs on your own computer with a web page and command line, and works with several AI providers, including local Ollama.
- Stars
- 250 +7 a day, est.
- Licence
- AGPL-3.0
- Runs on
- Your computer
- Setup
- Easy
- Language
- Python
- Age
- 35 days
What you can do with it
- Drop in PDF, Word, PowerPoint, Excel or Markdown files and have them filed automatically into folders of linked notes
- Ask questions and get answers that cite the notes used, so you can check the source
- Connect Claude Code, Codex or another MCP client so it can recall from and save to the wiki as long-term memory
Could replace
- Mem
Our suggestion based on what it does, not a feature-by-feature comparison.
Make money with it
A freelancer could offer to turn a client's scattered documents into an organised, question-answering Markdown knowledge base as a paid setup service.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Build a searchable internal knowledge base from policies, handbooks, proposals and client notes, with cited answers for staff or yourself
- Give an AI coding assistant a persistent memory of project documents so you spend less time re-explaining context
Can you use it commercially?
Free to use. Anything you distribute that includes it must be open-sourced under the same licence. Running it as an online service also counts, so a hosted version must offer its source.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Install with pip install llmwiki2 (Python 3.11 or later) or uv tool install llmwiki2, then run llmwiki2 and set up a provider in the browser; a desktop app is also available.
Follow the official instructions in the project README.
Things to check
- Needs an API key for a paid provider unless you use local Ollama
- The CROW classifier is remote by default, so document text may be sent to a third party unless you point it at a local server
- AGPL-3.0 licence and a contributor licence agreement, which may matter if you build a service on it
- The performance claims come from the authors' own benchmarks on a small, mostly Italian corpus
Checked 30 Oct 2026. Summary drafted by AI from the project's README.
