Agents with Laya

A port of the jev-ultrafast browser agent that decides with local laya-mlx instead of the hosted Jev API, covering DOM snapshot, executor and safety checks. Runs free on Apple Silicon.

Openlayer's library packs every eval for a trace into one decision request: tool choice, grounding, scope, injection, PHI. Runs on Jev, or on Kev or Laya locally on a Mac.

Describe a past conversation in plain language and Chat Seek finds it across local agent histories, reranks with the receptron Laya runtime, and offers a Resume action.

Typed-decision server on NVIDIA GPUs or Apple Silicon that speaks the Jev wire format, with coding-agent integrations. Built after a cat woke the author at five on a Sunday.

Nerve gives Hermes agents typed System One decisions, ranking, verification and an opt-in tool gate, using Jev or the open Laya model to oversee spending and risk.

Local decider for the browser-agent loop: hand it a numbered table of page controls and it picks the operation and element. Playwright/CDP driver, speaks /v1/systemone.

Allen Porter's native Assist conversation agent scores intents and entities in one Laya pass, runs device commands locally and escalates open-ended queries to a fallback LLM.

Six classifiers over SST-2, AG News and more, reporting accuracy, macro-F1, ECE, p50/p95 latency, throughput and cost side by side. Laya runs locally on MPS or CPU.

A browser agent that lets Laya choose among indexed on-page actions locally, completing a Google Flights search demo in about 6.5 seconds.

One process serves the model API and an admin UI; agents call decide over MCP, HTTP or CLI and take top.id as the action. Windows service installer included.

An OpenAI-compatible Go gateway where Jev or a local Laya picks which LLM answers each prompt, with a decision benchmark.

Cross-platform Agent Skill plus MCP tool that gives coding agents a local Laya decision capability. Verified on Apple Silicon with MLX and PyTorch backends.

Uses Laya on a CPU-only Cloud Run container to pick the right Gemini tier for each ADK request and scores the setup by cost per successful task.

The decision model never writes code; each step it picks the next tool, scores progress, estimates risk and says if the goal is reached. Any OpenAI-compatible LLM executes.

Hermes plugin that classifies each task against a ~300-skill index with Laya, injects the top skill's SKILL.md as per-turn context, and fails open. Cache-safe by design.

Pythongiant's OpenCode plugin continuously scores agentic drift with Laya plus Jensen-Shannon divergence, and plots drift over time. Code in pythongiant/laya-drift.

VeidtKV got Laya running on Radeon gfx1030 hardware, using a Hermes agent to do the porting. Code in Thotheris/laya-gfx1030.