Community runtime

Laya in Rust: sys1 and ollaya

Two community Rust servers that run Laya behind a Jev-compatible API: sys1 on candle, and ollaya, an Ollama-style CLI and daemon.

Rust servicesNo Python runtimeJev-compatible APICPU / CUDA / Metal
Quickstart
cargo install sys1 --features cpu
Source
alvarobartt/sys1

Community projects, not the upstream package. Check each repository for its license and supported models.

Usage
sys1 --model-id convaiinnovations/laya --dtype auto
# POST http://localhost:3000/v1/systemone

Two community projects run Laya from Rust, with no Python runtime on the serving machine. Both put Laya behind a Jev-compatible POST /v1/systemone API, so the same client code works with either one.

sys1: a Rust server built on candle

sys1 is a System One API server built with tokio, axum and serde, running Laya's ModernBERT encoder and decision heads on candle. Pick the backend when you install it:

cargo install sys1 --features cpu
cargo install sys1 --no-default-features --features metal   # Apple Silicon
cargo install sys1 --no-default-features --features cuda    # NVIDIA GPU

Start it with a Laya checkpoint:

sys1 --model-id convaiinnovations/laya --dtype auto

It listens on port 3000 and answers POST /v1/systemone and POST /v1/decide. Requests are batched dynamically by token count, and the project reports about 14 ms per query on an NVIDIA RTX Pro 6000. The README lists the English Laya checkpoint today, with more models planned.

ollaya: Ollama-style commands for decision models

ollaya works like Ollama: a daemon plus a CLI that pulls and runs decision models by name. It runs on ONNX Runtime on CPU, CUDA on NVIDIA GPUs, and natively on Apple Silicon.

curl -fsSL https://ollaya.dev/install.sh | sh
ollaya serve
ollaya run laya --preset triage "My payment failed twice"

laya routes between laya:en (ModernBERT-large, 421M) and laya:multilingual (mmBERT-base, 322M). ollaya also serves other decision models, such as Decider and NLI classifiers. It listens on port 11435, and the official TypeSafe SDK works unchanged with TYPESAFE_BASE_URL=http://localhost:11435. ollaya ships small ONNX graphs and reads the original weights from Hugging Face, checked by sha256, instead of re-hosting them.

Which one to use

sys1ollaya
Installcargo installInstall script, Docker or Windows installer
BackendsCPU, CUDA, MetalCPU (ONNX Runtime), CUDA, Apple Silicon
Default port300011435
Laya checkpointsEnglishEnglish and multilingual, via a router
Best forEmbedding a Rust server you build yourselfA ready-made local daemon with model management

Both are community projects, not part of the upstream Laya package. Check each repository for its license and current model support before you deploy.

Last verified against both repositories: September 25, 2026.