Neuron registration trends
The alpha price in τ, day by day, and what moved it each way.
Log change over the last 30 days +30.96%: protocol buys +0.78%, root sells −46.50%, users net −18.14%, cross-subnet +94.83%, unattributed −0.0007%.
The chart follows the alpha price in τ. Each period starts at its opening price and steps through the mechanisms below, in a fixed order, to its closing price: a step that rises pushed the price up, one that falls pushed it down, and its height is how far it moved the price. A thin line carries each close into the next period’s open; it is dashed where the two differ. The faint candle behind each period is the market’s own open, high, low and close, for context.
With many periods on screen (90 days, or hours), the steps would be too thin to read, so the chart draws the price as a line instead and colours each period by the mechanism that moved it most. Hover a period for the full step-by-step breakdown.
Not here, because they do not move the spot price: the per-block TAO injection into the pool, and burns.
All figures are log changes, not simple percentage changes, so the parts add up exactly to the total; on big moves the two differ (a 10% log fall is a 9.5% price fall).
2026-11-11 UTC, as of ≈14:57 UTC (block 9,483,777)
The day isn’t over yet, so these figures keep changing. They are in no daily total, average or rank.
Holder & circulating-alpha metrics as of (daily close)
Training robust robot policies requires evaluating performance across diverse task variations and scenes. Centralized approaches create bottlenecks in simulation capacity and introduce single points of failure in validation logic. A decentralized network can distribute the computational load of simulation while ensuring validators operate independently to score submissions fairly.
Attune addresses this by operating a distributed competition where miners submit policy weights, independent validators run duels in simulation to score them, and weights are calibrated on-chain based on those scores. This model removes centralized evaluation capacity constraints and creates economic incentives for both policy improvement and rigorous validation.
The subnet implements a king-of-the-hill mechanism: each queued policy submission duels the current champion on 240 simulation units seeded from finalized blocks. The challenger takes the crown when it beats the incumbent's success rate by 3+ percentage points.
The four most recent champions are cached by validators and mirrored to a public repository, ensuring reproducibility and removing dependencies on individual miners maintaining repositories.
Auto-generated from the GitHub repository and may not reflect the latest changes.
Attune is a Bittensor subnet for robot foundation models built by Robotensor. Miners submit policy weights for the Vector competition, where validators score them in simulation through a king-of-the-hill mechanism. Validators set weights on chain, with 30% of miner emission going to the policy competition and 70% to Attune Horizon, Robotensor's data collection platform.
Attune comprises three interconnected repositories: attune-subnet handles chain-side logic (commitments, queue management, block seeding, validator loop, and miner CLI); vector-orchestrator provides the duel engine, result storage, and runtime/protocol specifications; RoboTwin-Vector is a fork of RoboTwin 2.0 containing the simulation harness and task level gates. Miners submit only model weight files (model.safetensors) to gated Hugging Face repositories. Validators run three Python environments (3.10 for simulator, 3.12 for policy and host) on a single GPU machine, queue submissions in order, run duels against the reigning king, and publish winning weights to a public kings repository and on-chain.
The 4 most recent champions are cached locally and mirrored publicly. 70% of miner emission flows to the Horizon vault hotkey for off-chain data collection payments.
Each queued submission duels the current king on 240 units (16 tasks × 15 repetitions) seeded from the finalized block when the duel starts. The block must come after the commitment was made on chain. One submission per hotkey is allowed; later commitments from the same hotkey are refused while it remains in queue.
The lane will not accept a new submission from a hotkey until its previous one has completed or been dropped. Duplicate weights (identical to earlier commitments) are refused. Failed entries retry up to three times at least 90 seconds apart before being dropped.
Kings' models are kept by the validator and publicly mirrored so anyone can access the weights that won each crown.
The sections above were auto-generated from the GitHub repository and may not reflect the latest changes. View repository (github.com, opens in a new tab, external site)
The open frontier for adaptive robot intelligence
This information was auto-extracted from the GitHub repository and may be incomplete or out of date. Always refer to the subnet's GitHub repository (github.com, opens in a new tab, external site) for the latest instructions.
Not yet verified: Notes
Not yet verified: VRAM, GPU count, Storage, Network, Notes
Machine-extracted from the subnet's repository docs; may be wrong or out of date. Check the repository before buying or renting hardware. Open the repository (github.com, opens in a new tab, external site) · Extracted 9 Nov 2026
Install the Attune miner package from PyPI
pip install robotensor-attune
Validate that submission directory contains properly formatted model.safetensors weights
attune miner check --dir submission/
Set Hugging Face API token for repository access
export HF_TOKEN=...
Submit weights to a gated Hugging Face repository and commit on chain
attune miner submit --dir submission/ --repo <you>/vector-mine --network finney --netuid <N> --wallet.name miner --wallet.hotkey default
Make repository public after submission if still showing as private(optional)
attune miner reveal --repo <you>/vector-mine
Check submission status and queue position(optional)
attune miner status --hotkey <ss58> --network finney --netuid <N>
Clone required repositories
git clone -b vector https://github.com/robotensor/RoboTwin-Vector.git && git clone https://github.com/robotensor/vector-orchestrator.git && git clone https://github.com/robotensor/attune-subnet.git
Install RoboTwin-Vector simulator in Python 3.10 environment
cd RoboTwin-Vector && bash robotensor_bench/scripts/install_robotwin.sh
Create and populate Python 3.12 environment with subnet dependencies
uv venv --python 3.12 .venvs/subnet && uv pip install --python .venvs/subnet/bin/python -e attune-subnet -e vector-orchestrator -e vector-orchestrator/packages/vector-protocol -e vector-orchestrator/packages/vector-runtime
Create environment file with Hugging Face API token for validator account with permitted hub access
echo 'HF_TOKEN=hf_...' > config/.env
Configure validator with paths to simulator/policy Python binaries, simulator root directory, workers count, network, netuid, and wallet details
Create config/<network>.toml with [vector] section pointing to Python environments and wallet configuration
Start validator to begin queuing and dueling submissions
attune validator --config config/<network>.toml run
| Day (UTC) | Share |
|---|---|
| 2026-11-10 | 1.37% |
| 2026-11-09 | 1.18% |
| 2026-11-08 | 1.15% |
| 2026-11-07 | 1.04% |
| 2026-11-06 | 0.84% |
| 2026-11-05 | 0.25% |
| 2026-11-04 | 0.01% |
| 2026-11-03 | 0.02% |
| 2026-11-02 | 0.02% |
| 2026-11-01 | 0.03% |
| 2026-10-31 | 0.03% |
| 2026-10-30 | 0.03% |
| 2026-10-29 | 0.03% |
| 2026-10-28 | 0.03% |
| 2026-10-27 | 0.02% |
| 2026-10-26 | 0.02% |
| 2026-10-25 | 0.02% |
| 2026-10-24 | 0.02% |
| 2026-10-23 | 0.02% |
| 2026-10-22 | 0.02% |
| 2026-10-21 | 0.01% |
| 2026-10-20 | 0.0042% |
| 2026-10-19 | 0.0044% |
| 2026-10-18 | 0.0047% |
| 2026-10-17 | 0.01% |
| 2026-10-16 | 0.01% |
| 2026-10-15 | 0.01% |
| 2026-10-14 | 0.01% |
| 2026-10-13 | 0.01% |
| 2026-10-12 | 0.0009% |
| 2026-10-11 | 0.00% |
| 2026-10-10 | 0.00% |
| 2026-10-09 | 0.00% |
| 2026-10-08 | 0.00% |
| 2026-10-07 | 0.00% |
| 2026-10-06 | 0.00% |
| 2026-10-05 | 0.00% |
| 2026-10-04 | 0.00% |
| 2026-10-03 | 0.00% |
| 2026-10-02 | 0.00% |
| 2026-10-01 | 0.00% |
| 2026-09-30 | 0.00% |
| 2026-09-29 | 0.00% |
| 2026-09-28 | 0.00% |
| 2026-09-27 | 0.00% |
| 2026-09-26 | 0.00% |
| 2026-09-25 | 0.00% |
| 2026-09-24 | 0.00% |
| 2026-09-23 | 0.00% |
| 2026-09-22 | 0.00% |
| 2026-09-21 | 0.00% |
| 2026-09-20 | 0.00% |
| 2026-09-19 | 0.00% |
| 2026-09-18 | 0.09% |
| 2026-09-17 | 0.31% |
| 2026-09-16 | 0.39% |
| 2026-09-15 | 0.45% |
| 2026-09-14 | 0.52% |
| 2026-09-13 | 0.53% |
| 2026-09-12 | 0.56% |
| 2026-09-11 | 0.56% |
| 2026-09-10 | 0.52% |
| 2026-09-09 | 0.23% |
| 2026-09-08 | 0.00% |
| 2026-09-07 | 0.00% |
| 2026-09-06 | 0.00% |
| 2026-09-05 | 0.00% |
| 2026-09-04 | 0.00% |
| 2026-09-03 | 0.00% |
| 2026-09-02 | 0.00% |
| 2026-09-01 | 0.00% |
| 2026-08-31 | 0.00% |
| 2026-08-30 | 0.00% |
| 2026-08-29 | 0.00% |
| 2026-08-28 | 0.00% |
| 2026-08-27 | 0.00% |
| 2026-08-26 | 0.00% |
| 2026-08-25 | 0.00% |
| 2026-08-24 | 0.00% |
| 2026-08-23 | 0.00% |
| 2026-08-22 | 0.00% |
| 2026-08-21 | 0.00% |
| 2026-08-20 | 0.00% |
| 2026-08-19 | 0.00% |
| 2026-08-18 | 0.00% |
| 2026-08-17 | 0.00% |
| 2026-08-16 | 0.00% |
| 2026-08-15 | 0.00% |
| 2026-08-14 | 0.00% |
| 2026-08-13 | 0.00% |
