A three-model local image pipeline with a Laya style router
spoof.sh's ComfyUI workflow chains a Qwen prompt enhancer, a Laya router that picks the style and Qwen-Image on one NVIDIA card — about 37 seconds per image.
BUILDS
17 builds made with System One models.
Agents, routers, scorers and games — built on models that decide. Every entry links to the models it uses, so you can pull the same one and start from there.
17 builds
laya-browser-agent: local decisions for browser automation
Give it a numbered list of the page's controls and it picks the action and target — a drop-in for jev-ultrafast tooling that needs no screenshots.
laya-drift: how far has an OpenCode session wandered from its plan?
pythongiant's OpenCode plugin scores agent drift continuously with Laya and Jensen–Shannon divergence and charts it across the session.
Laya Router Skill for coding agents
An Agent Skill and MCP tool that gives Codex, Claude Code, OpenCode and Pi a local decision capability for routing work.
Laya Ultrafast: a local port of the jev-ultrafast browser agent
The browser-use agent's decisions move from the hosted Jev API to laya-mlx, keeping the DOM snapshot, executor and safety checks.
leanest: run only the end-to-end tests a PR can affect
Diffs the PR against main, asks one semantic yes/no per spec and runs just the affected tests, judged by a hosted or self-hosted Laya.
OpenClaw benchmark: Laya 85% at 28 ms, Jev 90% at 1.2 s
Aaron Edell compared laya-mlx with a hosted Jev tier and made the case for a Laya-first cascade.
pydecide: one Python client with fallback across decision backends
Typed questions against Jev, OpenRouter, Laya or cross-encoders, with a confidence policy that moves to the next backend on errors or low confidence.
A hypermedia browser that chooses links by meaning
Akihito Koriyama's Semantic Browser follows HAL links by their ALPS semantics, with Laya-MLX giving each link a probability.
Seven open decision models on JevBench in 21 minutes
yankis's video runs Nimble, Decider, OpenJev, Laya and others through the same JevBench scoring; Laya finishes last.
sysone-bench: Jev vs Laya on 751 identical questions
Sai Dutta's head-to-head: Jev leads on triage, guardrails, moderation and multilingual intent, while Laya wins on AG News.
jevals: agent evals and guardrails as typed decisions
Openlayer's library bundles the evaluations for an agent trace into one decision call, cheap enough to run on every trace — or free with local Laya.
laya-jev-lab: Laya first, Jev only when unsure
A local-first cascade: confident Laya answers run straight away and uncertain ones escalate to Jev, matching Jev's accuracy at 1.8× the speed.
laya_router: as accurate as GPT-5 nano at routing, 35× faster
Two routers behind one endpoint on 180 labeled requests; Laya picks small, medium or powerful in a single forward pass, for free.
Hermes skill_router: pick the right skill before the agent runs
A Hermes plugin that classifies each task against an index of about 300 skills with a local Laya model and injects the best match as context for the turn.
jeffrey: a coding-agent CLI where a decision model steers
At every step Jev or Laya picks the next tool, scores progress and estimates risk; the language model only executes and never decides.
A Laya browser agent trained on Mind2Web
Chooses the next web action with Laya, trained and evaluated on the Mind2Web benchmark; the weights are on Hugging Face.
Many of the first builds here were collected by madewithlaya.com. Every entry links to its creator’s own post, repository or site.