Le catalogue réel des outils pour IA

Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.

Evaluate state with typed choice, score, and probability questions.

MCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities.

Evidence-oriented code questions, diff review and test selection via a Jev endpoint.

Typed decisions with Jev / System One via OpenRouter or TypeSafe: classify, verify, rerank, decide.

Local Issue triage with optional Jev judgments and calibrated acceptance gates.

MCP server over TypeSafe Jev: typed ask, rank and check judgments return calibrated probabilities.

Hand browser work off to a server-side agent: read the page as a table, act, then verify.

Jev judgments for agents: injection scanning, shell risk gating, ranking

Set the style guidance for an executive report

Set the style guidance for an executive report

Typed Jev decisions in one batched tool: choice, score, and yes/no probabilities.

A design-style library for AI agents: search real styles, fetch a ready-to-apply design spec.

Citation Style Language locale shape, body discarded

Instagram-style shard id shape, value discarded

Typed yes/no, pick-one and score judgments from Jev in one batched call; typed escalation back.

Prose linter + AI-slop detector: weasel words, passive voice, hedging, and research-cited AI tells

Set confirmation style for a delivery workflow

MCP server for generating Chromium-style QR codes with optional Dino logo or custom center image

Register a delivery confirmation pattern