Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.
Knowhere is a document-processing memory layer that turns unstructured PDFs, office files, images, tables, Markdown, and text into structured, navigable information for AI agents. It supports agentic RAG and other LLM workflows by preserving context while parsing documents, extracting hierarchies, and building graphs. The catalogue instruction helps coding agents use Knowhere.
Latest release v1.2.31 · 26 Oct 2026
1 file for Codex and OpenCode: knowhere AGENTS.md — 7,477 tokens loaded in every session.
AGENTS.md A 7,477 tok These files are Ontos-AI/knowhere's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.