Repository

stera-sdk

Python SDK for Stera: Record, Process, Evaluate, and Export Multimodal Data

README

<h1 align="center">
<img alt="" src="assets/logo_light.png" height="32" align="center" style="vertical-align: middle;">
 Stera SDK
</h1>

by FPV Labs (fpvlabs.ai)

PyPI Python License

<a href="https://fpvlabs.ai/app">

Scan to get the iOS app

</a>

stera-sdk is the Python SDK behind Stera (website · iOS app).

Load MCAP recordings, run swappable hand, face, and skeleton models behind one schema,
and visualize or export clean episodes, ready for embodied AI, VLAs, and world models.

Quick Start

import stera
from stera.data import MCAPReader
from stera.models import HandTracker, FaceBlurrer
from stera.viz import Visualizer
from stera.processing import MeshRefiner
from stera.eval import Evaluate

session = MCAPReader("recording.mcap")
hands   = HandTracker(model="mediapipe")
blur    = FaceBlurrer(model="mediapipe")
viz     = Visualizer(session, map_3d="auto")

for frame in session.frames():
    blurred = blur.blur(frame)
    poses   = hands.detect_hands(frame)
    session.add_rgb_frame(frame.index, blurred)
    session.add_hand_pose(frame.index, poses)
    viz.log_frame(frame, hands=poses)

mesh = MeshRefiner(session).refine()           # clean + densify + colorize
session.export("episodes/run_01", visualizer=viz, mesh=mesh)
Evaluate(session).show()                       # interactive HTML QC report

Stera SDK

Getting started

pip install "stera-sdk[all]"

Documentation

License

Apache 2.0 © FPV Labs