Cached at:
09/25/26, 07:16 PM
# Ollaya — Run decision models locally.
Source: [https://ollaya.dev/](https://ollaya.dev/)
Ask typed questions about any text or JSON and get calibrated answers in milliseconds\. Private, open source, on your own hardware\.
[Download](https://ollaya.dev/download)[Browse models](https://ollaya.dev/search)
Real output: routed tolaya:en, answered in 8\.9 ms on an RTX 4090\.
- [Fast](https://ollaya.dev/#fast)
- [Drop\-in compatible](https://ollaya.dev/#compatible)
- [Open models](https://ollaya.dev/#models)
- [Your data stays yours](https://ollaya.dev/#private)
- [Platforms](https://ollaya.dev/#platforms)
## Fast
Decisions in milliseconds\.
A decision model answers in a single forward pass, with no token\-by\-token generation\. On your own GPU, a five\-question request to Laya takes about 10 ms, end to end through the HTTP API\.
Every model, one scale· median latency, lower is better- laya:multilingual8\.1 ms
- laya:en9\.6 ms
- gliclass14\.7 ms
- nli20\.4 ms
- decider:0\.8b155 ms
- decider:2b190 ms
- TypeSafe Jevhosted API236–276 ms
Ollaya: median of a five\-question request through the HTTP API on an NVIDIA RTX 4090 \(laya in fp16, the others in fp32\)\. Jev: median request latency of the hosted API in third\-party benchmarks \([AbdelStark/jev\-benchmarks](https://github.com/AbdelStark/jev-benchmarks),[nibzard/decision\-model\-benchmark](https://github.com/nibzard/decision-model-benchmark)\), which includes the network\. Setups differ, so read it 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](https://ollaya.dev/docs/typesafe-compatibility)
## 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\.
## Platforms
Runs where you work\.
A desktop app and a command line for macOS, Windows and Linux, and a Docker image for servers\. Every model runs on the CPU; an NVIDIA GPU on Linux, in WSL 2 or in Docker takes a request down to milliseconds\.
[Install for your platform](https://ollaya.dev/download)NVIDIA GPUs need driver R580 or newer; the installers fetch the CUDA libraries only when they find one\. On Apple, AMD and Intel GPUs, models run on the CPU\.
## Get up and running in minutes\.
One binary, one command:`ollaya run laya`\.
[Download](https://ollaya.dev/download)
macOS, Windows, Linux and Docker · Apache\-2\.0 ·[GitHub](https://github.com/ollaya-dev/ollaya)