/ DOCUMENTATION
Connect a rig and stream data in minutes.
Everything you need to integrate Telemanual — the Python SDK, REST and gRPC APIs, the ROS 2 adapter, and export formats.
QUICKSTART
Install & connect
Install the SDK, authenticate, and register your first rig.
bash
$ pip install telemanual-sdk
$ telemanual login # opens browser auth
$ telemanual rigs add my-arm-01 --sdk ros2PYTHON SDK
Register sensors & stream
Declare the topics you care about; Telemanual handles time-sync, calibration checks, and upload.
stream.py
from telemanual import Rig, Sensor
rig = Rig("my-arm-01")
rig.add(Sensor.camera("/wrist/rgb"))
rig.add(Sensor.joints("/joint_states"))
rig.connect()
rig.stream(export="lerobot") # live → cloudREST & gRPC API
Pull datasets anywhere
$ curl -H "Authorization: Bearer …" \
api.telemanual.ai/v1/datasets/dpv2RESTgRPC streamingwebhooks
ROS 2 ADAPTER
Drop into your graph
$ ros2 launch telemanual_ros \
capture.launch.py rig:=my-arm-01HumbleIronJazzy
/ KEEP READING
Middleware and toolingROS 2Record robot demonstrations from a live ROS 2 graph with rosbag2, avoid the QoS and clock pitfalls that corrupt recordings, and export to training formats.6 min readTraining and datasetsLeRobotLeRobot is Hugging Face's robotics library. Here is how a Telemanual export maps onto LeRobotDataset, and how to load, train, and evaluate against it.5 min readTraining and datasetsPyTorchTurning a captured robot dataset into a PyTorch pipeline — Dataset choices, video decode bottlenecks, episode-safe splits, and reproducible sampling.5 min readData formatsMCAPMCAP is a self-describing, chunked, indexed log format for timestamped multimodal messages, and the default ROS 2 bag storage plugin since Iron.6 min read