OpenKB: what it is, what problem it solves & why it's gaining traction

What it solves

OpenKB transforms raw, fragmented documents into a structured, interlinked wiki-style knowledge base. Unlike traditional RAG, which retrieves information from scratch for every query, OpenKB compiles knowledge into a persistent, evolving wiki where information compounds over time, reducing the need to re-derive insights from raw data repeatedly.

How it works

OpenKB uses a two-layer architecture: a wiki foundation and generators.

1. Wiki Foundation: It converts various file formats (PDF, Word, PowerPoint, etc.) into Markdown. For long documents (20+ pages), it uses PageIndex to create a hierarchical tree index instead of reading the full text. An LLM then compiles these documents into summaries, concept pages, and entity pages (people, organizations, places, products) with cross-links.
2. Generators: These tools use the compiled wiki as a substrate to produce outputs, such as grounded answers to queries, interactive chat sessions, 3D knowledge graphs, and HTML slide decks.

Who it’s for

It is designed for users who need to manage large volumes of complex documents and want a persistent, structured knowledge base that can be integrated with tools like Obsidian or used to power specialized AI agents.

Highlights

• Vectorless Retrieval: Uses reasoning-based tree indexing via PageIndex for long documents rather than a vector database.
• Citations and Synthesis: Automatically generates summaries and cross-references across multiple documents.
• Skill Factory: Distills knowledge from the wiki into portable agent skills for use in Claude Code, Codex, and Gemini CLI.
• Obsidian Compatibility: Stores the wiki as plain Markdown files with wikilinks, making it natively compatible with Obsidian's graph view.
• Multi-modality: Capable of retrieving and understanding figures, tables, and images.