ORO
Reinforcement-learning environments and benchmarks for commerce agents: ShoppingBench and ORO Bench, where an agent shops against a simulated shopper and a changing market and is graded on the order it places, plus AssistantEval for delegated service tasks; an open-source competition on Bittensor Subnet 15 with a public leaderboard and a Python SDK for miners, scored trajectories published on Hugging Face; teams request a sample of data and environments, with no published price.
What it does
- Evaluation and observability
- Model training
Features 6
- Commerce environmentsTrains and evaluates agents on economic decisions.
- Open-source competitionAgents compete on benchmarks and generate scored trajectories.
- ORO BenchAn environment compiler for agentic shopping tasks.
- Compete on Subnet 15Submit shopping agents and race on a public leaderboard.
- Samples for your researchTeams request data, environments and a sample.
- Published trajectoriesScored trajectories are released as a Hugging Face dataset.
Sources
- Pricing
-
Official documentation · 18 Oct 2026
Home page: the call to action reads Request a sample; no plan or price is published on the pages read.
- Description
-
Official documentation · 18 Oct 2026
Home page: "We train and evaluate agents in environments shaped by economic decisions."
- What it does
-
Official documentation · 18 Oct 2026
Home page: "We train and evaluate agents in environments shaped by economic decisions."
- Sold within
-
Sold by request for a sample; no self-serve plan or price appears on the pages read.
- Name
-
Official documentation · 18 Oct 2026
Name as published on the product page.
- URL
-
Official documentation · 18 Oct 2026
Product page, read 2026-10-18.
- Deployment
-
Official documentation · 18 Oct 2026
The pages read state no deployment model beyond the vendor-run service; saas is recorded as the vendor-operated reading.
- Interfaces
-
Official documentation · 18 Oct 2026
Docs: contents list an API overview with authentication and a Python SDK for miners, and a web dashboard.
Something wrong here? Send a correction — quote this product id: oro-ai-environments.