Laya for Rust
Rust has several independent Laya runtimes. Some load the upstream safetensors directly with Hugging Face candle, others run ONNX exports or ggmlc GGUF files, and a few wrap the model in a Jev-compatible HTTP server.
77 projects
laya-gateway
aios-b-612
Routes coding-agent tool choices through Laya in a local LLM gateway
@zatsepin/jigor
zatsepin
Offers a CLI and HTTP gateway for local ONNX Laya and von models and remote Jev decisions
IC-Laya-Standalone
humandebri
A Rust implementation runs Laya checkpoints for inference in Internet Computer canisters
mahabodi
jollypk
Combines topology memory and ONNX Runtime-based Laya decisions in a System-1 engine for AI agents
laya-workflow
oliveagle
Ports a workflow engine to Rust and includes an inference crate that serves the Laya model
qa-intent
zjarlin
A Rust CLI that generates QA banks and compiles them into Laya/Jev decision requests
laya_demo_test
j75689
A Snake demo compares Python and Rust Laya runners with ONNX Runtime and Core ML backends
laya-onnx-android
rookery-labs
Runs Laya as an Android System-1 decision engine with ONNX Mobile and a Rust JNI tokenizer
laya-seo
emmanuelnurit
Provides SEO and GEO audits through a Jev-based CLI and MCP, with a local Laya scoring bridge
laya-snake
deepondas
Runs the Laya decision model as it plays Snake in a live 3D game
sys1rust
kgarg2468
A Rust and MLX service runs Laya decision models locally and exposes the System 1 API
layagrep
asherepenko
Searches repositories by natural-language questions using a local Laya decision model
laya-terminal-pong
victormartinho360
Implements terminal Pong with Laya-controlled paddles through a local HTTP server
sysone
inovacc
A Rust binary runs Laya through ONNX Runtime and serves the System One HTTP protocol
laya-rust
lengoman
Provides an idiomatic Rust client for evaluating typed decisions with Laya
laya-rs
ParkSnoopy
Provides a Rust/Burn runtime for Laya inference with Python fine-tuning and ONNX export
bevy_laya
ParkSnoopy
Connects Laya inference to Bevy through an asynchronous request and response adapter
burn-laya
ParkSnoopy
Runs typed local inference for Laya on Rust/Burn and provides fine-tuning and ONNX export tools
ducktape-laya
adrian729
Embeds local Laya GGUF inference through C++, Rust, Node.js and experimental browser bindings
laya-siro
Cihaimasuiro
Runs Laya decisions in a low-memory Windows automation engine using Rust and ONNX Runtime
orphusbot
kelvincushman
Provides self-hosted task bots that use Laya for routing and checking risky actions
laya-hub
surtr85
Routes MCP servers and agent skills using Laya System-1
jev-local
orthagonal
Provides a Rust decision-model server with configurable Laya, Jev, and other backends
smart-computer-use
lindoelio
Provides a desktop computer-use agent skill with optional local Laya decision-model integration
Libraries
laya-rust is a pure-Rust port on candle with no Python, torch or ONNX export step. It runs on CPU, Metal or CUDA:
cargo build --release # CPU, library + laya CLI
cargo build --release --features metal # Apple GPU
cargo build --release --features cuda # NVIDIA
let agent = Agent::from_dir("models/laya-base", Options::default())?;
let response = agent.system_one(&json!("Charged twice for order #4417."), &questions)?;
It also includes a local web console (--features serve) and an exfil_triage example. The README reports it catches 10 of 11 credential-exfiltration commands on a thirty-command held-out set at a 0.5 threshold.
laya-candle is another candle port with a Router, loading checkpoints from the Hub (Rust 1.88+):
[dependencies]
laya-candle = "0.1"
serde_json = "1"
Servers
sys1 is a System One compatible API server on axum and candle, with token-based batching:
cargo install sys1 --features cpu
sys1 --model-id convaiinnovations/laya --dtype auto
It answers at /v1/systemone, and its README reports about 14 ms per query on an NVIDIA RTX Pro 6000.
Also: ollaya, an Ollama-style daemon written in Rust; laya-rs, a Linux CPU server on ONNX Runtime; and laya-goish, which serves ggmlc GGUF files.
Apps
laya-pong is a browser Pong game with the physics in WebAssembly and the decision from native Laya over HTTP, at 18.7 ms p50 on Metal according to its README. keel is a Rust/GPUI coding workspace with a local Laya selector.
Caveats
laya-rust builds f32 only on CPU, because candle has no f16 CPU kernels. That doubles the weights to 1.69 GB resident. laya-rs uses POST /v1/system-one (with a hyphen), so it is not a drop-in Jev endpoint. Its README says so directly.
More ways to use Laya