Overview

HybridDB is one embedded database object that unifies SQLite rows, FTS5 keyword search, ChromaDB vectors, optional DuckDB analytics, and NetworkX graphs — with a self-healing journal and versioned tables.

HybridDB gives agents persistent, searchable memory — one embedded database object that coordinates SQLite, FTS5 keyword search, ChromaDB vector search, optional DuckDB analytics, and optional NetworkX graphs, all kept in sync by a self-healing journal.

It is embedded, local, and open source: no cloud APIs, no vector DB services, no internet connection required. Ships as a single Python package with zero external infrastructure dependencies. Used in production by the Executive Assistant agent system.

30-second start

from hybriddb import HybridDB, LONGTEXT, TEXT

db = HybridDB("./my_data")
db.create_table("docs", {"title": TEXT, "body": LONGTEXT})

db.insert("docs", {"title": "Getting Started", "body": "A guide to using HybridDB..."})
db.insert("docs", {"title": "API Reference", "body": "Full API documentation..."})

# Search every text column
db.search_all("docs", "getting started")

# Search one column — hybrid is the default (keyword + vector, RRF-fused)
db.search("docs", "body", "how do I begin", mode="hybrid")

# Structured query with parameters
db.query("docs", where="title LIKE ?", params=("%start%",))

Why HybridDB?

Every serious project that needs both keyword and semantic search ends up wiring SQLite + FTS5 + ChromaDB together by hand: schema creation, FTS5 triggers, Chroma collection management, keeping them in sync, recovering from crashes, rebuilding indexes. HybridDB does all of that once, done right.

What’s inside

Feature status

Built on

Source of truth for this page: HybridDB · open-assistants-lab/HybridDB