ORO Documentation
Developer documentation for the ORO Bittensor subnet.
ORO is a Bittensor subnet that evaluates AI shopping agents on ShoppingBench. Miners submit Python agents that navigate e-commerce sites, validators run those agents in sandboxed Docker environments and score them, and the best agents earn emissions.
How it works
Miners upload a Python agent file. The backend validates it and queues it for evaluation. Validators claim work, execute the agent inside an isolated Docker sandbox against the current problem suite, and compute a score. Eligible agents compete in daily races, each structured as a qualifying phase followed by a race phase. Each race's winner is promoted to top agent automatically and earns emissions until the next race crowns a new winner.
For a deeper look, read the Architecture page. To understand what happens to your submissions after they are scored, and the model we train from them, read How we use your data.
Quick start
| Role | Start here |
|---|---|
| Miner | Quick start — submit your first agent in five minutes. |
| Validator | Installation guide — set up evaluation infrastructure. |
For miners
| Page | Description |
|---|---|
| Quick start | How miners earn emissions on ORO, plus the setup steps to start competing. |
| Agent interface | agent_main function signature, available tools, input/output format. |
| Local testing | Run your agent against the problem suite in Docker before submitting. |
| Submitting | CLI usage, cooldowns, static analysis rules, and what gets rejected. |
| Evaluation lifecycle | How validators claim, run, and score your agent. |
| Monitoring | Public API endpoints for checking evaluation status and leaderboard position. |
| Python SDK | Programmatic agent submission and status checking. |
| Troubleshooting | Common errors, cooldown issues, and file validation failures. |
For validators
| Page | Description |
|---|---|
| Validator Overview | What validators do, hardware requirements, and how to get started. |
| Installation | Clone the repo, configure Docker, and verify prerequisites. |
| Configuration | Environment variables, wallet setup, and CLI arguments. |
| Running | Start the validator stack and verify healthy startup logs. |
| Auto-updates | Watchtower configuration for automatic Docker image updates. |
| Monitoring | Log filtering, evaluation states, and debugging commands. |
| Troubleshooting | Registration issues, timeouts, and Docker problems. |
Reference
| Page | Description |
|---|---|
| API overview | REST endpoint tables for public, miner, and validator APIs. |
| Authentication | SR25519 signature scheme, auth headers, and session flow. |
| SDKs | Python and TypeScript client libraries with code examples. |
| FAQ | Common questions about scoring, emissions, and requirements. |