Local Laya System-1 judge MCP server + skill for oh-my-pi: typed decisions in milliseconds, zero LLM tokens
Local System-1 judge for oh-my-pi, powered by laya. Typed decisions (choice/bool/score) in ~1s on CPU, 0 LLM tokens burned, nothing leaves the machine.
Measured head-to-head on the same classification questions (real model via omp -p vs this plugin on CPU, no GPU):
LLM judge() laya-judge --------- latency / question ~18s (16–25s sampled) ~0.35s (0.2–0.5s) tokens / question ~700 0 accuracy (12-case bench) n/a (reference) 8/12, misses escalate chance (2–3 vs 0), not a checkpoint coronation.
Grounded quiz (python demo/quiz.py): 6/8, mean 282ms, 0 tokens — both misses came in under 0.2 confidence, exactly the cases the escalate rule covers.
Snake (python demo/snake.py): score 12, 300 moves, alive, 12 shield interventions, ~0.9s/move on CPU, 0 tokens. Watch every decision in the browser: open web/snake.html (canvas replay with live probability bars, play/pause/speed/scrub); quiz at web-quiz.html. Recipe (from laya-mlx): a deterministic planner describes each direction over a tiny state (Safe route: yes. Food reachable: a safety shield executes the best SAFE move. Short parallel criteria are the whole trick — greedy end-to-end choice without the planner scores 0 (see demo/snake.py header for the measured failure modes). Honest calibration: per-move confidences on game states run at noise level (0.005-0.05; the quiz gets 0.2-1.0 on text) — navigation is planner + shield with laya ranking, the same division of labor as laya-mlx. The maze variant (demo/maze.py) is a documented negative: corridors trap the noise walk (1 crumb/200 steps).
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/F0Rextasy--omp-laya-judge.html)
Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to th
dontpayfull/AInotateAnnotated screenshots for AI agents: Skitch-style arrows, numbered steps, boxes, labels, solid redaction
MohammadHijjawi97/since-cutoffFind which APIs of your pinned Python dependencies changed after your coding model's training cutoff, and give the agent short AGENTS.md / CLAUDE.md notes from a static API diff. No model calls, no AP
osaxyz/sepiaceLong-term memory for coding agents. The sepiace plugin for Claude Code and Codex.
sepehr071/awesome-iran-mcp19 open-source MCP servers (308 tools) that give AI agents the Iranian web: Digikala, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche and more. Prices in Toman.
PyModel/jev-judge-mcpTyped judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.