Kwipu
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts enti
What is Kwipu?
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
Overview of Kwipu
What it is
Kwipu turns a folder of documents into a property-graph RAG index that you can explore and query from an interactive terminal, a 3D web interface, or an MCP client. It works with ordinary knowledge folders and Obsidian-style vaults. The system can run fully locally when a local Ollama LLM and embedding model are selected; the default LLM is gpt-oss:20b-cloud, which can send data to its provider.
Key features
- Builds a property graph from
.md,.txt,.pdf, and.docxdocuments. - Extracts semantic relations with an LLM and structural relations from wikilinks and YAML frontmatter.
- Combines vector similarity, BM25, temporal metadata, and optional synonym retrieval.
- Grounds answers in source chunks and returns citations.
- Visualizes entities, documents, and relations in an interactive 3D graph.
- Watches the source folder and updates persisted storage safely.
- Supports English, Italian, French, German, Spanish, and Portuguese patterns.
Use cases
- Querying project context, roles, and tasks directly from a terminal.
- Reconstructing changes across meetings and reviews.
- Comparing people, roles, and supporting documents.
- Exploring the knowledge graph and asking questions from a browser.
- Connecting an AI client over the MCP protocol.
Getting started
powershell git clone https://github.com/benmaster82/Kwipu.git Set-Location .Kwipu py -3.12 -m venv .venv .venvScriptsActivate.ps1 python -m pip install --upgrade pip==25.1.1 python -m pip install -r .bridgerequirements.txt ollama pull nomic-embed-text ollama pull gpt-oss:20b-cloud # or a local model python .geode_graph.py --fast See the repository README for full setup including the web interface and MCP server.
License and pricing
Licensed under MIT. Open source.
Based on the project's public README and repository metadata.
