The real catalog of tools for AI agents

Set up the JEV model router for Claude Code, Codex and Cursor, and install MCP servers.

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

Typed Jev decisions in one tool: choice, score, yes/no probabilities via any compatible endpoint.

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

Grade essays, check resumes, and ask typed yes/no, choice and rubric questions, powered by Jev.

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

Read-only VibeRaven guides: explain a finding, search launch guides, get a Supabase checklist.

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

Lint Jev and Luna decision-model questions, or ask the model to check them with your key.

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

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

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

Set source-agreement guidance

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

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

SMM panel catalog: cheapest services across panels, Trust Scores, reviews, comparisons, panel tools

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

TVmaze shows, people, next episodes in your timezone, episode guides, schedules, and credits.

Set severity-based assignment guidance

Windows GUID braces shape, value discarded