AI Agent
Laya Studio hosts the open-source Laya System One decision model behind a Jev-compatible API: send state and typed questions, get answers with probabilities in one forward pass, plus optional MCP tools and a guard endpoint.
Browse curated shortlists where this tool appears.
Related picks from editorial notes.
Also mentioned
Full overview from our catalog (read-only reference).
Editorial notes to help compare fit before opening the vendor site.
Context from the listing review and editorial research.
NEW tool. Product/site is Laya Studio; model family is Laya. DISAMBIGUATION: independent hosted service, not affiliated with TypeSafe or Convai per laya.studio/llms.txt; not Layla companion apps. Cloudflare's Oct 2026 Clef launch blog benchmarks Laya as very low latency but weaker on several quality suites versus Clef/Jev — treat vendor benches as directional and run your own evals. Open-source model + commercial API.
In-depth description and capability notes.
POST https://api.laya.studio/v1/systemone (Jev-compatible wire format) Batch endpoint up to 64 states; up to 32 questions per request (per docs) Choice, score, and noul question types with confidence Open-source Laya model (Apache-2.0, Convai Innovations checkpoints) hosted independently MCP server for Claude/Cursor (decide, classify, yes_no, score, ask, guard_check) Laya Guard for tool-call allow/ask/block verdicts Optional Swiss-only residency mode (higher credit rate) New workspaces get a small free token allowance
Teams that want System One decisions with a hosted autoscaled API, MCP access for agents, or a lower list price than TypeSafe Jev while keeping a similar request shape.