neuroflow-sdk 0.1.0

Python SDK for NeuroFlow — the hardware-agnostic neural data platform. Connect to EEG/BCI devices, stream real-time data, and extract features with zero neuro-expertise required.

NeuroFlow SDK for Python

Build brain-computer interfaces in Python. Connect to 20+ EEG/BCI devices, stream real-time neural data, extract features, and run ML predictions — with zero neuroscience expertise required.

from neuroflow import Client

client = Client(base_url="http://localhost:8000", api_key="your-key")

# Discover and connect
devices = client.discover_devices()
device = client.connect(devices[0].id)

# Stream with real-time features
session = device.start_session()
for packet in session.stream():
    print(f"Focus: {packet.features.focus_score:.2f}")
    print(f"Alpha: {packet.features.band_powers['alpha']:.2f}")

session.stop()

Installation

pip install neuroflow

For local device access (no server needed):

pip install "neuroflow[local]"

Quick Start

Remote Mode (via API server)

from neuroflow import Client

client = Client(base_url="http://localhost:8000", api_key="your-key")

# List available devices
devices = client.discover_devices()

# Connect and start session
device = client.connect(devices[0].id)
session = device.start_session()

# Get features
features = session.get_features()
print(f"Band powers: {features.band_powers}")
print(f"Focus score: {features.focus_score}")

session.stop()
device.disconnect()

Local Mode (direct device access, no server)

from neuroflow import LocalClient

# Connect to synthetic board for development
client = LocalClient(board_id=-1)
client.connect()

# Start streaming
client.start_stream()
data = client.get_data(num_samples=512)

# Extract features locally
features = client.get_features()
print(f"Alpha power: {features.band_powers['alpha']:.4f}")

client.stop_stream()
client.disconnect()

Async Streaming

import asyncio
from neuroflow import AsyncClient

async def main():
    client = AsyncClient(base_url="http://localhost:8000", api_key="your-key")

    devices = await client.discover_devices()
    device = await client.connect(devices[0].id)
    session = await device.start_session()

    async for packet in session.stream():
        print(f"Focus: {packet.features.focus_score:.2f}")
        if packet.features.focus_score > 0.8:
            print("High focus detected!")
            break

    await session.stop()

asyncio.run(main())

Features

• 20+ Device Support — Muse, OpenBCI, Emotiv, BrainBit, g.tec, and more via BrainFlow
• Real-Time Processing — Sub-millisecond Rust-accelerated DSP pipeline (0.18ms P95)
• Feature Extraction — Band powers, spectral entropy, Hjorth parameters, connectivity metrics
• ML Inference — ONNX model deployment for focus detection, relaxation, and custom classifiers
• Dual Mode — Remote (API server) or Local (direct device access)
• Type-Safe — Full Pydantic models with type hints throughout
• Async Support — Native async/await with AsyncClient

Supported Devices

Device	Board ID	Protocol
Synthetic (dev)	-1	Simulated
Muse 2	22	Bluetooth
Muse S	21	Bluetooth
OpenBCI Cyton	0	Serial
OpenBCI Ganglion	1	Serial/BLE
Emotiv Insight	25	Bluetooth
BrainBit	7	Bluetooth
... and 20+ more

Documentation

• Quickstart Guide
• Python SDK Reference
• API Reference

License

MIT