Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.kiwifs.com/llms.txt

Use this file to discover all available pages before exploring further.

KiwiFS is a knowledge filesystem server — one Go binary that turns markdown on disk into a searchable, queryable, versioned knowledge base accessible via REST, MCP, NFS, S3, WebDAV, and FUSE.

​
Why KiwiFS?

AI agents need somewhere to store and retrieve knowledge. Traditional databases require schemas and drivers. File-based wikis lack search and structure. KiwiFS gives you both:
  • Files are the truth — every page is a plain markdown file with YAML frontmatter. No proprietary format, no lock-in.
  • Agents already know the API — cat, grep, echo work out of the box. No SDK needed.
  • Every write is a git commit — full history, blame, diff, and rollback for free.
  • Full-text + vector search — BM25 via SQLite FTS5 out of the box, with pluggable vector embeddings.
  • Query language (DQL) — SQL-like queries over frontmatter metadata.
  • Web UI included — wiki links, knowledge graph, block editor, comments, dark mode.
  • Single binary, zero config — download and run. No Node, no Docker required (Docker optional).

​
How it works

All protocols flow through the same storage layer. Every write — regardless of how it enters — gets a git commit, a search index update, and an SSE broadcast.

​
Next steps

Quickstart

Install and run KiwiFS in 60 seconds.

Configuration

Configure search, auth, versioning, and more.

Agent Interface

How AI agents read and write knowledge.

MCP

Connect Claude, Cursor, and other AI tools.
Last modified on May 4, 2026