Quickstart

Install and run KiwiFS in 60 seconds.

1. Install

   Shell

   curl -fsSL https://raw.githubusercontent.com/kiwifs/kiwifs/main/install.sh | sh
   

   Homebrew

   brew install kiwifs/tap/kiwifs
   

   Go

   go install github.com/kiwifs/kiwifs@latest
   

   Docker

   docker run -p 3333:3333 -v ./knowledge:/data ameliaanhlam/kiwifs
   

   The Docker image runs kiwifs serve with default settings. Skip to step 4 — init and serve are handled automatically.

2. Initialize a knowledge base

   kiwifs init --template kb --root ./knowledge
   

   This creates a directory with starter files, a schema, and an agent playbook.

   Templates: kb, wiki, memory, tasks, data, cms, runbook, adr, prompt, research, log, and blank. See Init templates.

3. Start the server

   kiwifs serve --root ./knowledge
   

   KiwiFS is now running at http://localhost:3333. Open it in your browser to see the web UI.

4. Write from your agent

   Via REST

   curl -X PUT 'http://localhost:3333/api/kiwi/file?path=concepts/auth.md' \
     -H "X-Actor: my-agent" \
     -d "# Authentication
   
   OAuth2 + JWT based authentication system."
   
5. Search

   curl 'http://localhost:3333/api/kiwi/search?q=authentication'
   

   You now have a searchable, versioned knowledge base. Every write is a git commit.

Connect an AI agent

Add KiwiFS as an MCP server in Claude Desktop or Cursor:

{
  "mcpServers": {
    "kiwifs": {
      "command": "kiwifs",
      "args": ["mcp", "--root", "/path/to/knowledge"]
    }
  }
}

Your agent now has access to 71 MCP tools for reading, writing, searching, querying, drafts, and more. See MCP for the full tool reference.

Next steps

Configuration

Auth, search, versioning, vector embeddings, and more.

Agent Interface

Filesystem, REST, and MCP access patterns.

Search

Grep, FTS5, hybrid, and vector search.

DQL

Query frontmatter metadata with a SQL-like language.

Deploy with Docker

Production deployment with Docker Compose.

Web UI

Tree, editor, graph, Bases, and search.