User repository on GitHub
Blazing fast, self-hosted structured decisions for open models with a TypeSafe AI compatible API, written in Rust.
- Forks
- 4
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Rust server that exposes a System One compatible API at /v1/systemone for self-hosted Laya checkpoints with token-based batching.
User repository on GitHub
Blazing fast, self-hosted structured decisions for open models with a TypeSafe AI compatible API, written in Rust.
Repo stats from the GitHub API, cached Oct 2026.
Blazing fast structured decisions for System One open-models self-hosted with a TypeSafe AI compatible API, written in Rust. tokio, axum and serde, the usual suspects. SDPA on CPU, Metal, and CUDA. Flash Attention on Ampere, Ada Lovelace, and Hopper. Blazing fast inference for ModernBERT and Qwen3.5. Multimodal decisions from text, images, and video when supported by the model. Rust and Cargo 1.98.1, mandatory. ffmpeg and ffprobe 6.1.1 or higher for video inputs.
Quoted from the project's README. Read the full README.
Watch out
Only the listed Laya checkpoints are documented, and CPU, Metal and CUDA builds use different features. Copy reviewed against the repository README on 2026-10-04, not from running it.
Original write-ups on what this entry is for.
Posts from builders shipping with Jev right now.