wangmiaozero/laya-router-skill
laya-router
VerifiedCross-platform local decision routing for AI coding agents using Laya and Laya-MLX. Use for fast task classification, complexity estimation, model escalation hints, tool-use routing, and lightweight risk assessment. Advisory only.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.6 KB |
| agents/openai.yaml | config | 219 B |
| assets/icon.svg | other | 2.9 KB |
| references/AGENTS.md | markdown | 1.1 KB |
| references/AGENT_E2E.md | markdown | 8.2 KB |
| references/ARCHITECTURE.md | markdown | 1.2 KB |
| references/BACKENDS.md | markdown | 967 B |
| references/RC_VALIDATION.md | markdown | 5.0 KB |
| scripts/decide.py | script | 561 B |
| scripts/decide.shexecutable | script | 64 B |
| scripts/healthcheck.py | script | 3.3 KB |
| scripts/healthcheck.shexecutable | script | 69 B |
| scripts/install.ps1 | script | 226 B |
| scripts/install.py | script | 12.3 KB |
| scripts/install.shexecutable | script | 65 B |
| scripts/uninstall.py | script | 6.5 KB |
| scripts/uninstall.shexecutable | script | 73 B |
references/ARCHITECTURE.md
View on GitHub# Architecture
```text
AI agents (ChatGPT Desktop (Codex), Codex CLI, Claude Code, OpenCode, Pi)
-> Agent Skill -> laya-router CLI
-> optional MCP adapter
-> RouterCore -> LayaBackend
-> laya-mlx / MLX (Apple Silicon)
-> upstream laya / PyTorch (other platforms)
```
The CLI is the stable entry point. MCP exposes `laya_decide`, `laya_health`, and `laya_info` over stdio and shares the core. The runtime never executes model output. All errors yield `status=unavailable`, `advisory=true`, and `fail_open=true`. In `backend=auto`, Apple Silicon tries MLX then PyTorch. An explicit backend never silently changes.
The upstream Router handles language and checkpoint selection. Its model instances are lazy and retained in the long-running process, with at most two loaded at once. A separate CLI process has a separate lifetime; use MCP for hot repeated requests.
The Python environment and config live in a platformdirs user data directory. Agent skill links point to a separate copied skill tree. The installer records ownership in `install-manifest.json`; uninstall consults that file before deletion.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |