Laya in coding tools

Coding agents make many cheap judgement calls: which files matter, how hard a task is, whether a command is risky. Several projects hand those calls to a local Laya model instead of a second LLM call, which saves tokens and keeps code on the machine.

128 projects

laya-guard

chetas1208

Adds an advisory Laya classifier signal to deterministic guardrails for AI applications

0·GitHub repo

PythonModeration & safety

laya-guard-trial

Ayaannnnnnn

Lets users test Laya-based shell-command judgments for an agent safety hook

0·HF Space

PythonBrowser

aitomaton

sirmmo

Analyzes infrastructure errors and dispatches coding agents based on rules, Laya, Jev, or other LLMs

0·GitHub repo

PythonAgents

pi-laya-mlx

a3harva

Screens coding-agent tool calls with a fine-tuned Laya model running locally on Apple Silicon

0·GitHub repo

PythonMLX

ReflexFoundry

nazeeh111

Trains and evaluates local Laya decision heads for coding-agent workflows

0·GitHub repo

PythonAgents

alvaress

GitHub Actions

Installs an OpenCode agent harness that makes local decisions with Laya and validates code changes

0·npm package

Node.jsONNX

layagrep

gak4u

A Python pipeline fine-tunes Laya for code-relevance decisions used by jevgrep

0·GitHub repo

PythonFine-tunes & weights

laya-zcode-stack

Ydjin1984

Runs a local Laya decision engine and ZCode plugin with MCP tools for coding-agent workflows

0·GitHub repo

GoONNX

Claude Code

laya-codex indexes a repository locally and gives Claude Code the relevant code before each task, using tree-sitter, BM25 and a Laya re-ranker. Install (macOS Apple Silicon or Linux x86_64):

curl -fsSL https://raw.githubusercontent.com/pilotspace/laya-codex/main/install.sh | sh

/plugin marketplace add pilotspace/laya-codex
/plugin install laya-codex@laya-codex

Its README reports that Claude Code read 38% fewer code tokens and took 21% fewer turns in a paired benchmark of 60 tasks on three repositories.

arbiter serves Laya behind a Jev-compatible API with an MCP server and a Claude Code plugin.

Model routing in coding agents

pi-pignon asks a local laya-serve (or Jev) how hard each prompt is and switches the pi agent's model:

pi install npm:pi-pignon
uv tool install "laya[serve]"
LAYA_HOST=127.0.0.1 laya-serve

Judges and gates

adecider: typed judgements for any coding agent through a CLI, MCP tool or HTTP, with local Laya as the default backend.
omp-laya-judge: a local judge for oh-my-pi. It reports a mean 160 ms per question on CPU and 8/12 correct on its benchmark.
laya-rust: its exfil_triage example flags shell commands that send credentials off the machine.

Workspaces

keel is a local-first macOS coding workspace. A local Laya selector (Core ML) or an opt-in hosted Jev picks a route for each new task, and the host validates the choice before applying it.

Caveats

omp-laya-judge found Laya confidently wrong on arithmetic and parity questions (confidence 0.80 and 0.84), so it routes those to the LLM whatever the confidence. Keep Laya on semantic questions and keep a fallback. laya-codex downloads a model of about 850 MB on install.

Hosted option

Several tools on this page can talk to Jev instead of a local model. Anything built on the official TypeSafe SDKs can point at a hosted Laya instead: layahost documents the switch as changing TYPESAFE_BASE_URL and the key. That saves a model download on every developer machine, at the cost of sending prompts and code snippets to a server in the EU. layahost is run by the makers of laya.tools.