TAO $223.71+2.6% 24h
68

NOVA

sn68Inference & ComputeClean18Strong entry81

No description set on the registered repo.

Emission
23.3
TAO / day · live
Alpha
0.0954
τ · mcap 360.7K
Top-slot payout
0.502
τ per winning epoch · live
Stars
21
live from the GitHub API
Primary language
Python
repo-reported
Last push
7d ago
feeds the dormancy integrity signal
Topics
repo-declared tags

About the repo

what the project says about itself — the input for semantic labels

metanova-labs/nova/· pushed 7d ago

No description set on the repo.

Reading this tab

scope of the data

Taonets fetches the repo's public metadata (description, topics, language, stars, last push) and the head of its README. Commit-count histories, contributor lists and release notes require the GitHub commits/releases endpoints, which the worker doesn't consume yet — those panels are coming with the ingest upgrade and are not simulated in the meantime.

README head

first lines of the default branch README, unedited

# NOVA - SN68

## High-throughput ML-driven drug screening.

### Accelerating drug discovery, powered by Bittensor.

NOVA harnesses global compute and collective intelligence to navigate huge unexplored chemical spaces, uncovering breakthrough compounds at a fraction of the cost and time.

## System Requirements

- Ubuntu 24.04 LTS (recommended)
- Python 3.10 - 3.12
- CUDA 12.6 (for GPU support)
- Sufficient RAM for ML model operations
- 2 GPU devices with > 48 GB VRAM for parallel inference. If only one is available, inference will run sequentially which may result in delayed/missing scoring rounds.
- Internet connection for network participation

## Installation and Running

1. Clone the repository:
```bash
git clone --recurse-submodules https://github.com/metanova-labs/nova.git
cd nova
```

2. Prepare your .env file as in example.env:
```
# General configs
SUBTENSOR_NETWORK="wss://entrypoint-finney.opentensor.ai:443" # or your chosen node
BT_NO_PARSE_CLI_ARGS=false # false to enable parsing of CLI args

# GitHub authentication
GITHUB_TOKEN="your_personal_access_token"

# Parallel inference settings:
# The values are illustrative, but should work for most machines 
# you can use tools/calibrate_perf.py to get the most optimal values for you specific environment
NOVA_BOLTZ_SHARDS=12
NOVA_BOLTZ_GPUS=0,0,1,0,0,1,0,1,0,1,0,1
NOVA_BOLTZGEN_GPUS=1
NOVA_BOLTZ_THREADS=1
NOVA_MAX_CONCURRENT_TNP=16

# GitHub configs - FOR MINERS
GITHUB_REPO_NAME="repo-name"
GITHUB_REPO_BRANCH="repo-branch"
GITHUB_REPO_OWNER="repo-owner"
GITHUB_REPO_PATH="" # path within repo or ""

# For validators
VALIDATOR_API_KEY="your_api_key"
AUTO_UPDATE="1" # Set to "0" to disable auto-updates (not recommended)
```

3. Install dependencies:
   ```bash
   ./install_deps.sh [--cuda <version>] && source "$HOME/.local/bin/env"  #cuda version is optional, default is 12.6
   ```

4. Run:
```bash
# Activate your virtual environment:
source .venv/bin/activate

# Run your script:
# miner:
python3 neurons/miner.py --wallet.name <your_wallet> --wallet.hotkey <your_hotkey> --logging.info

# validator:
python3 neurons/validator/validator.py --wallet.name <your_wallet> --wallet.hotkey <your_hotkey> --logging.debug
```

## Configuration

The project uses several configuration files:
- `.env`: Environment variables and API keys
- `requirements/`: Dependency specifications for different environments
- Command-line arguments for runtime configuration

### GitHub Authentication

Set up GitHub authentication:
1. Create a [Personal Access Token](https://github.com/settings/personal-access-tokens/new) on GitHub
2. For validators: No specific permissions needed (read-only access)
3. For miners: Grant repository access permissions for your submission repository

## For Validators

DM the NOVA team to obtain an API key.


## Support

For support, please open an issue in the repository or contact the NOVA team.
GitHub · Taonets