Skip to main content
Use the Aria Compute Playground to try AFM chat, ROUTER decision routing, AGENT sessions, and MEMO memory storage.

What you can try

  • AFM Base Model: chat against an OpenAI-compatible AFM endpoint.
  • ROUTER Decision Routing: the same chat UX through aria-router, with strategy choices for Semantic / Agent / Decision Model. Gold virtual models:
    • ariacompute/semantic-auto
    • ariacompute/agent-auto
    • ariacompute/afm-d-auto
  • AGENT: sessions against the cloud agent runtime (aria-agent-cloud).
  • MEMO memory storage: try the sandboxed aria-memo instance. Write tiered memories, run hybrid search (with an optional graph-aware mode and an inspectable RetrieveTrace), pure-vector recall, and batch search-batch, then explore the four-view relation plane with connect / relate / relations / graph. A JSON/text toggle lets you compare parsed results with native CLI output. See the aria-memo CLI guide for command details.
ROUTER, AGENT, and MEMO playgrounds run on sandboxed backend pools, so concurrent users never share router, agent, or memory state.

Account

Some Playground actions need a signed-in Aria Compute account on the same site (.com or .cn). See Authentication for sign-in, and Sites & regions for per-site wallets and API keys.

Next steps