BluPe Spotter

API

DreamZero moves. Spotter watches, repairs failures, and hands control back. Paper · Code · Robot API

Checking Spotter configuration…

Run locally through a subscription

Paste this into your coding assistant

Clone https://github.com/andlyu/blupe-remote-yam.git and launch ./run-playground.sh. Help me connect Codex or Claude using my subscription.

Live views, synchronized. Checking stream

Top Connecting
Observer Connecting
Left Connecting
Right Connecting
—:—

Live decisions

Spotter’s observations and repair decisions will appear here.

Checking / unavailable

Task chat

Spotter decisions

Runner: —

Prompt

Waiting for someone to run a policy.

Response notes

Waiting for a run
  1. Astra’s replies and robot feedback from the current run appear here for everyone.

Settings

Choose Astra or GPT 6.1+, or Claude Opus 5.5+. You can enter a new model ID directly.

The model observes the cameras, chooses a move, and waits for robot feedback before deciding again.

Your name, task, and readable Astra conversation will be visible to everyone watching.

This project is super new. We'd love to follow up about your experience.

Models can take a while. I’d rather watch a sped-up video by email once the run is complete, not while it’s running.

Optional · Sent after completion.

Select model and run

min

Paste the following prompt into your favorite coding agent:

Checking the connection uses a small amount of subscription usage.

Connecting to your browser session…

All episodes

View Dataset in HF

Open dataset here

Your runs

Runs from your current session.

Your runs will appear here.

    All runs

    Models: All models

    Select All models to clear the model filter. On desktop, hold Command or Ctrl to select several.

    Observed rates on the selected user-labeled tasks. Different task mixes are not a controlled benchmark. Unlabeled and excluded runs stay visible.

    Loading past runs…

    Hover for a quick preview. Select a recording to watch the full run.

      How to use the playground

      1. Choose a robot and model. Open the model menu to set up your connection and run duration.
      2. Describe the task. Send your prompt to join the queue. Watch the cameras and follow the robot’s progress in task chat.
      3. Review the run. Browse recordings below, or open the dataset to explore the camera and action data.

      API docs ↗Run locally ↗ASPIRE README ↗

      Keys stay out of logs. Robot controls stay with your session.

      Past run

      Runner assessment

      Assessment revision history

        Run totals

        Email me the video

        We’ll send this replay as an MP4 attachment when it fits, plus a link to watch it.