All decision model projects

Codex skill and MCP for advisory Jev decisions in Java/Maven backend work: file relevance, change risk, SQL risk and more.

Local Laya decision layer for DeepSeek Harness: routes prompts, gates risky tool calls and swaps models, all offline at no token cost.

Portable decision layer for agent harnesses: Jev picks from host-supplied capabilities while the host keeps permissions and execution.

Chrome extension that badges X and LinkedIn posts READ, MAYBE or SKIP against your plain-English interest profile as you scroll.

Neovim popup showing jev-lens verdicts after Claude Code edits: whether to look, which files, and debris to strip.

Fuzzy linter hook for Claude Code and Codex where Jev checks each written file against team rules and reports violations at edit time.

Natural-language linter combining ast-grep selectors with Jev to catch misleading names, stale comments and tests that miss their claims.

Linter for Obsidian vaults and LLM wikis that flags contradictions, stale claims, unresolved markers and dangling links with Jev.

GitHub Action that reviews repository files against your yes/no questions with Jev and passes only when every answer meets its threshold.

One Jev call per log batch answers noise and severity questions; code maps answers to suppress, watch, review, notify or page.

Gmail classifier running on Google Apps Script where Jev decides action-needed, importance and category for each thread.

Chrome/Brave extension that uses Jev to classify, label and safely bulk-clean a Gmail inbox with undo.

Dry-run-first Proton Mail Bridge triage on macOS where Jev answers whether each message is spam or phishing.

Maps each Python function to the tests that run it; Jev scores candidate function-test links that static analysis misses.

Jev browser agent that pierces shadow DOM and iframes, adds canvas fallback and full actions, with one Jev request per cycle.

Eval-first MCP server for Jev: prototype questions, map them over many items, and measure accuracy and thresholds on labelled data.

Unofficial, read-only MCP server exposing Jev as four advisory tools: decide, route, risk score and yes/no gate.

MCP server giving any agent Jev's classify, score, yes/no check and allow/confirm/block gating of risky tool calls.

Rust MCP server for Codex that hands classification, relevance, candidate selection and evaluation to Jev with accept/verify policies.

MCP server exposing Jev-style decision models served locally by Ollama's /v1/systemone as classify, yes/no and score tools.

Standalone MCP server for T3 Code with one jev_route tool where Jev picks a model and reasoning-effort combination for a task.

Python FastMCP server wrapping Jev's noul, choice and score judgments, with configs for many coding agents and an OpenCode Zen route.

MCP server exposing Jev as one evaluate tool, plus a harness comparing Jev's judgments with general LLMs on shared datasets.

Dependency-free Python MCP server (Spanish docs) exposing Jev to coding agents through ask_jev and list_jev_models.

MCP server that lets Claude Code or Codex drive real Chrome with Jev picking elements and checking steps, plus safety gates and traces.

npm MCP server and Claude Code plugin exposing Jev classify, score, check and batched-ask tools with full probability distributions.

Self-hosted Jev MCP server for Claude Code and Codex with confidence gating, cost guardrails, caching and decision logs.

Self-hosted Jev MCP gateway on Cloudflare Workers with nine tools for intent routing, reranking and batch judgments.

PyPI MCP server for Jev with choice, score, noul, compare, verify and batch classify tools plus a one-command client installer.

Java/Spring Boot MCP server exposing Jev classify, score, check and patch-gate tools over HTTP instead of stdio.