crewai-hatidata

CrewAI integration for HatiData -- Memory and Tools that let CrewAI agents query, explore, and persist data in HatiData's in-VPC warehouse.

Installation

pip install crewai-hatidata

Quick Start

from crewai import Agent, Task, Crew
from crewai_hatidata import HatiDataQueryTool, HatiDataMemory

query_tool = HatiDataQueryTool(host="proxy.internal", agent_id="analyst")
memory = HatiDataMemory(host="proxy.internal", agent_id="analyst")

agent = Agent(
    role="Data Analyst",
    tools=[query_tool],
    memory=memory,
)

Features

• HatiDataQueryTool -- Execute SQL queries against HatiData from CrewAI agents
• HatiDataListTablesTool -- Discover available tables in the warehouse
• HatiDataDescribeTableTool -- Inspect table schemas and column types
• HatiDataContextSearchTool -- Full-text context search for RAG workflows
• HatiDataMemory -- Persistent agent memory backed by HatiData
• Agent-aware billing -- Every query is tagged with agent ID for per-agent cost tracking
• Sub-10ms latency -- Queries execute in-VPC with no data leaving your network

Components

Documentation

Full documentation is available at docs.hatiosai.com/hatidata.

License

Apache License 2.0. Copyright (c) Marviy Pte Ltd. See LICENSE for details.