MCP servers and agent skills with decision models

CLI and agent skill that shortlist notes in Obsidian or Logseq locally, then have Jev rerank them, returning original passages.

Agent skill that grills a plan as a design-tree interview, using Jev for typed judgments along the way.

Coding-agent skill that drives Chrome over CDP to hunt for jobs on company sites, with Jev scoring every link and job posting.

Minimal demo that matches a user goal to the best MCP server or capability in a catalogue using Jev, in two stages for large catalogues.

Library and MCP server that scores a fixed set of choices with a model you already run (llama.cpp, Ollama, OpenRouter).

Local MCP server giving Claude Code, Codex, Cursor and OpenCode per-dimension Jev quality scores on their code while they work.

Agent skill that sends closed coding-agent judgments to Jev before asking the user, before risky commands and after failures.

Rust engine that answers noul, choice and score from any LLM in one prefill via logprobs, wire-compatible with /v1/systemone and MCP.

Open calibrated decision models from 400M to 80B with Jev-compatible server, MCP server and clients, benchmarked against Jev.

Experimental Hermes Agent plugin for bounded Jev worker checkpoints, route advisories and request-goal tools.

Kotlin NES emulator whose agent plays Super Mario Bros. and Final Fantasy, with a local model choosing from the goals that apply each turn.

Agent skill that tells you when you need an eval and how to build it, with an opt-in lane routing closed-label residue to Jev.

Jev-powered browser MCP server that makes each step in one parallel call and escalates to the driving LLM only when unsure.

CLI and MCP server giving coding agents Jev-powered semantic search, focused reads and list picking in about a second for about a cent.

Weekly go-to-market workflows built on Jev, such as lead triage and deal risk, each tested against Claude.

Code Mode for MCP where retrieval shortlists tools and Jev picks one or says none fits, benchmarked on several tool-use suites.

Awesome list of Jev projects sorted by what you would install, with a know-before-you-build section on limits and an agent skill.

Chinese case library of Jev posts and open-source projects, packaged as an agent skill that suggests how Jev could fit your task.

Community directory of Jev apps, resources and runnable offline examples, with a guide skill and a searchable JevList web UI.

Automated, source-backed catalog of 862 Jev projects in four languages, with per-entry relationship and evidence notes and an agent skill.

Browsable directory of 50 runnable Jev judge evals and 1,300+ community builds, also served to agents via MCP and llms.txt.

Installable agent skills for triage, routing, code review and document work with Jev, plus 108 scenarios and recorded examples.

Single-tool MCP server that acts as a content-moderation gate using Jev, with noul, choice and score question types and a mock mode.

Experimental Rust SEO and GEO CLI and MCP server combining page checks, DuckDuckGo queries and optional Jev scoring.

Single-tool MCP server that acts as a code-review gate powered by TypeSafe Jev.

Claude Code and Codex skills powered by Jev, published with a calibration curve measured on 4,995 real agent decisions.

OpenRouter's catalogue of decision models from several publishers behind its alpha Decisions API, with an agent-skill usage guide.

MCP server demo exposing TypeSafe System One noul, choice and score judgments as agent tools.

TypeSafe's official cookbook for a two-stage skill-suggestion workflow that selects a skill and can reject the shortlist.

classifier.dev: free zero-shot classification HTTP service built on Jev, with no API key or account and an agent skill.