Skip to content

Run decision models locally.

Ask typed questions about any text or JSON and get calibrated answers in milliseconds. Private, open source, on your own hardware.

$ ollaya run laya --preset triage "I was charged twice for my subscription this month and want a refund."

Answers returned by the model
QuestionAnswerP
intentrefund1.00
is_urgentno0.88
frustration1.76 / 30.36
refund_requestedyes0.90
churn_riskno0.61

$

Fast

Decisions in tens of milliseconds.

A decision model answers in a single forward pass, with no token-by-token generation. Measured through the full HTTP API on an RTX 4090, a five-question request to Laya takes 8–10 ms.

Latency for one question · lower is better
  • Laya multilingual32.8 ms
  • Laya39.5 ms
  • TypeSafe Jev (p50)236–276 ms

Laya figures are from the Laya model card, measured on an NVIDIA Tesla T4. Jev p50 range from third-party benchmarks (AbdelStark/jev-benchmarks, nibzard/decision-model-benchmark). Setups differ, so treat this as an order-of-magnitude comparison.

Drop-in compatible

Speaks TypeSafe's API.

Ollaya serves /v1/systemone and /v1/models with TypeSafe's request and response shapes. The official TypeSafe Python SDK 0.7.1 works unchanged against a local server.

Request

# Point the TypeSafe SDK at Ollaya
export TYPESAFE_BASE_URL=http://localhost:11435
export TYPESAFE_API_KEY=local        # any value works
export TYPESAFE_DEFAULT_MODEL=laya

# …or call the compatible endpoint directly
curl http://localhost:11435/v1/systemone -d '{
    "model": "laya",
    "state": "Can I get an invoice for last month?",
    "questions": {
      "intent": {
        "type": "choice",
        "instructions": "What does the customer want?",
        "criteria": {
          "invoice": "Needs an invoice or receipt",
          "refund": "Wants money back",
          "other": "Anything else"
        }
      }
    }
  }'

Response

{
  "model": "laya:en",
  "answers": {
    "intent": {
      "type": "choice",
      "choice": "invoice",
      "confidence": 0.9547,
      "probabilities": {
        "invoice": 0.9698,
        "refund": 0.0172,
        "other": 0.013
      }
    }
  },
  "usage": {
    "input_tokens": 43,
    "output_tokens": 0
  }
}

TypeSafe compatibility guide

Open models

Open weights, ready to pull.

Start with Laya from Convai Innovations: an English model, a 100+ language model, a model fine-tuned for typed decisions, and a router that picks for you.

Your data stays yours

Private by default.

Tickets, emails and user messages are often the most sensitive data you have. With Ollaya they are scored where they already live.

  • Local

    Runs on your machine with ONNX Runtime, on the CPU or an NVIDIA GPU. The server listens on 127.0.0.1 by default.

  • Open weights

    Weights come from their authors’ Hugging Face repositories, pinned to a commit and checked against sha256. Ollaya never re-hosts them, and the runtime is Apache-2.0.

  • No per-token fees

    Run as many decisions as your hardware can handle. No metering and no API bill.

  • Calibrated

    Probabilities you can put thresholds on. Laya’s calibration error (ECE) is 0.081 after temperature fitting, vs 0.246 for Jev.

Get up and running in minutes.

One binary, one command: ollaya run laya.

Linux, macOS and Docker · Apache-2.0 · GitHub