Sidekick Innovations

Engineering Blog

Introducing the Sidekick API

One endpoint for every robotics foundation model, and a Python client, sidekick-sdk, built to run on the robot instead of in a data center.

Read more→
Engineering Blog

An Update on the Sidekick Flywheel

The Sidekick Flywheel nearly tripled task success on towel folding, lifting the success rate from 18.0% to 51.5%.

Read more→
Emergent Capability

Sidekick's First Emergent Capability

In a self-improving robot-learning loop, data-generation throughput rose as an emergent, unrewarded byproduct of reinforcement learning.

Read more→
Engineering Blog

Out of the Loop

Token Fusion's first application: learning in deployment, without a person watching.

Read more→
Engineering Blog

Sidekick Token Fusion

A frozen vision-language model already understands the scene. We take that understanding and fuse it into how our robots learn and act.

Read more→
Engineering Blog

🔁 Sidekick Learning Loop

Introducing the Sidekick Learning Loop - Reinforcement Learning in the Real World.

Read more→
Research

💬 PromptVLA

An open challenge to map the behaviors and limits of prompted Vision Language Action models.

Read more→
Engineering Blog

🤝 Sidekick GPU Handshake

How we solved the compute war inside the robot to achieve 70x faster performance.

Read more→
Engineering Blog

✍️ RLHF for Robots

Building the reinforcement learning feedback loop that transformed language models, now for physical robots.

Read more→

Latest News