KotaDB

A custom database for distributed human-AI cognition, built entirely by LLM agents.

🚀 Quick Start - Choose Your Language

pip install kotadb-client

npm install kotadb-client

cargo add kotadb

# Will be available soon at:
# go get github.com/jayminwest/kota-db/clients/go

⚡ 60-Second Quick Start

Get from zero to first query in under 60 seconds:

Option 1: Docker (Easiest)

# One command to start everything
docker-compose -f docker-compose.quickstart.yml up -d

# Run Python demo (shows all features)
docker-compose -f docker-compose.quickstart.yml --profile demo up python-demo

Option 2: Shell Script (Local Install)

# One-liner installation and demo
curl -sSL https://raw.githubusercontent.com/jayminwest/kota-db/main/quickstart/install.sh | bash

Option 3: Manual Setup

# Start server
docker run -p 8080:8080 ghcr.io/jayminwest/kota-db:latest serve

# Install client and try it
pip install kotadb-client
python -c "
from kotadb import KotaDB, DocumentBuilder
db = KotaDB('http://localhost:8080')
doc_id = db.insert_with_builder(
    DocumentBuilder()
    .path('/hello.md')
    .title('Hello KotaDB!')
    .content('My first document')
)
print(f'Created document: {doc_id}')
results = db.query('hello')
print(f'Found {len(results.get(\"documents\", []))} documents')
"

🎉 That's it! You're now running KotaDB with type-safe client libraries.

KotaDB combines document storage, graph relationships, and semantic search
into a unified system designed for the way humans and AI think together.

Performance

Real-world benchmarks on Apple Silicon:

10,000 document dataset, Apple Silicon M-series

🎯 Complete Examples

Production-ready applications demonstrating real-world usage:

🌐 Flask Web App

Complete web application with REST API and UI

cd examples/flask-web-app && pip install -r requirements.txt && python app.py
# Visit http://localhost:5000

📝 Note-Taking App

Advanced document management with folders and tags

cd examples/note-taking-app && pip install -r requirements.txt && python note_app.py
# Visit http://localhost:5001  

🧠 RAG Pipeline

AI-powered question answering with document retrieval

cd examples/rag-pipeline && pip install -r requirements.txt && python rag_demo.py
# Requires OPENAI_API_KEY for best results

⚡ Quick Examples

# Python type-safe usage
from kotadb import KotaDB, DocumentBuilder, ValidatedPath

db = KotaDB("http://localhost:8080")
doc_id = db.insert_with_builder(
    DocumentBuilder()
    .path(ValidatedPath("/notes/meeting.md"))
    .title("Team Meeting")
    .content("Discussion about project timeline...")
    .add_tag("meeting")
    .add_tag("important")
)

# Advanced search with filters
from kotadb import QueryBuilder
results = db.query_with_builder(
    QueryBuilder()
    .text("project timeline") 
    .tag_filter("meeting")
    .limit(10)
)

🦀 Rust (Full Feature Access)

# Clone and build
git clone https://github.com/jayminwest/kota-db.git
cd kota-db && cargo build --release

# Start server
cargo run --bin kotadb -- serve

# CLI operations  
cargo run --bin kotadb -- insert /docs/rust.md "Rust Guide" "Ownership concepts..."
cargo run --bin kotadb -- search "ownership"  # Full-text search
cargo run --bin kotadb -- search "*"          # List all documents  
cargo run --bin kotadb -- stats              # Database statistics

just dev              # Auto-reload development server
just test             # Run comprehensive test suite
just check            # Format, lint, and test everything
just bench            # Performance benchmarks
just release-preview  # Preview next release

Architecture

┌─────────────────────────────────────────────────────────────┐
│                    Query Interface                           │
│              Natural Language + Structured                   │
├─────────────────────────────────────────────────────────────┤
│                    Query Router                              │
│         Automatic index selection based on query             │
├──────────────┬───────────────┬───────────────┬──────────────┤
│   Primary    │   Full-Text   │     Graph     │   Semantic   │
│   B+ Tree    │    Trigram    │  (Planned)    │     HNSW     │
├──────────────┴───────────────┴───────────────┴──────────────┤
│                    Storage Engine                            │
│        Pages + WAL + Compression + Memory Map                │
└─────────────────────────────────────────────────────────────┘

Core Features

Storage

• Native Format: Markdown files with YAML frontmatter
• Git Compatible: Human-readable, diff-friendly
• Crash-Safe: WAL ensures data durability
• Zero Database Dependencies: No external database required

Indexing

• B+ Tree: O(log n) path-based lookups
• Trigram: Fuzzy-tolerant full-text search
• Graph: Relationship traversal (MCP tools only, not fully implemented)
• Vector: Semantic similarity with HNSW

Safety

• Systematic Testing: 6-stage risk reduction methodology
• Type Safety: Validated types (Rust compile-time, Python/TypeScript runtime)
• Observability: Distributed tracing on every operation (Rust only)
• Resilience: Automatic retries with exponential backoff (all client libraries)

Code Examples

Rust (Full Feature Access)

use kotadb::{create_file_storage, DocumentBuilder};

#[tokio::main]
async fn main() -> Result<()> {
    // Production-ready storage with all safety features
    let mut storage = create_file_storage("~/.kota/db", Some(1000)).await?;
    
    // Type-safe document construction
    let doc = DocumentBuilder::new()
        .path("/knowledge/rust-patterns.md")?
        .title("Advanced Rust Design Patterns")?
        .content(b"# Advanced Rust Patterns\n\n...")?
        .build()?;
    
    // Automatically traced, validated, cached, with retries
    storage.insert(doc).await?;
    
    Ok(())
}

Python (Client Library)

from kotadb import KotaDB, DocumentBuilder, QueryBuilder, ValidatedPath

# Connect to KotaDB server
db = KotaDB("http://localhost:8080")

# Type-safe document construction (runtime validation)
doc_id = db.insert_with_builder(
    DocumentBuilder()
    .path(ValidatedPath("/knowledge/python-patterns.md"))
    .title("Python Design Patterns")
    .content("# Python Patterns\n\n...")
    .add_tag("python")
    .add_tag("patterns")
)

# Query with builder pattern
results = db.query_with_builder(
    QueryBuilder()
    .text("design patterns")
    .limit(10)
    .tag_filter("python")
)

TypeScript (Client Library)

import { KotaDB, DocumentBuilder, QueryBuilder, ValidatedPath } from 'kotadb-client';

// Connect to KotaDB server
const db = new KotaDB({ url: 'http://localhost:8080' });

// Type-safe document construction (runtime validation)
const docId = await db.insertWithBuilder(
  new DocumentBuilder()
    .path("/knowledge/typescript-patterns.md")
    .title("TypeScript Design Patterns")
    .content("# TypeScript Patterns\n\n...")
    .addTag("typescript")
    .addTag("patterns")
);

// Query with builder pattern and full IntelliSense support
const results = await db.queryWithBuilder(
  new QueryBuilder()
    .text("design patterns")
    .limit(10)
    .tagFilter("typescript")
);

Query Language

Natural, intuitive queries designed for human-AI interaction:

// Natural language
"meetings about rust programming last week"

// Structured precision
{
  type: "semantic",
  query: "distributed systems",
  filter: { tags: { $contains: "architecture" } },
  limit: 10
}

// Graph traversal
GRAPH {
  start: "projects/kota-ai/README.md",
  follow: ["related", "references"],
  depth: 2
}

Project Status

Complete

• Storage engine with WAL and compression
• B+ tree primary index with persistence
• Trigram full-text search with ranking
• Intelligent query routing
• CLI interface
• Performance benchmarks

In Progress

• Model Context Protocol (MCP) server
• Python/TypeScript client libraries
• Semantic vector search
• Graph relationship queries

Documentation

Architecture • API Reference • Development Guide • Agent Guide

Installation

Client Libraries

Python

pip install kotadb-client

TypeScript/JavaScript

npm install kotadb-client
# or
yarn add kotadb-client

Go (Coming Soon)

# Go client is currently under development
# See https://github.com/jayminwest/kota-db/issues/114
# Will be available at: github.com/jayminwest/kota-db/clients/go

Server Installation

As a CLI Tool

cargo install kotadb
# or from source:
cargo install --path .

kotadb serve                    # Start HTTP server
kotadb insert /path "Title" "Content"  # Insert document
kotadb search "query"           # Search documents

As a Rust Library

[dependencies]
kotadb = "0.3.0"
# or from git:
kotadb = { git = "https://github.com/jayminwest/kota-db" }

Docker

# Using pre-built image (recommended)
docker pull ghcr.io/jayminwest/kota-db:latest
docker run -p 8080:8080 ghcr.io/jayminwest/kota-db:latest serve

# Or build from source
docker build -t kotadb .
docker run -p 8080:8080 kotadb serve

Language Support Matrix

Legend: ✅ Complete • 🚧 In Progress • ❌ Not Available

*Query routing happens automatically on the server for client libraries

Benchmarks Detail

Contributing

This project is developed entirely by LLM agents. Human contributions follow the same process:

1. Open an issue describing the change
2. Agents will review and implement
3. Changes are validated through comprehensive testing
4. Documentation is automatically updated

See AGENT.md for the agent collaboration protocol.

License

MIT - See LICENSE for details.

_{Built for KOTA • Inspired by LevelDB, Tantivy, and FAISS}

_{The best database is the one designed specifically for your problem.}