All decision model projects

Claude Code (and Codex) plugin that trims long Bash output chunk by chunk with Jev before it reaches the model, without summarising.

Fast browser-use layer for coding agents: Jev picks the operation and target element each step, via MCP server or CLI.

Typed-decision accuracy layer for RAG: six checks for intent, relevance, clarification, sufficiency, grounding and caveats.

chrome-devtools-mcp plus one 'reach' tool: Jev walks the browser to the right spot so the agent makes a single devtools call there.

Filters an assistant's memories by relevance, not resemblance: one Jev yes/no per memory in a single request, kept above a threshold.

Java tool that sorts each claim in a rental listing into verify on site, demand evidence or high-risk pitch, building a viewing checklist.

Terminal REPL for shaping System One requests before writing code, with lessons, a sketch editor, conversation turns and offline simulation.

Python library that scores each RAG passage with a Jev Score question in one batched call, then sorts and filters by threshold.

Agent skill and Python library for Claude Code and Codex that reranks candidate lists with one Jev yes/no relevance question each.

Drop-in rerank API that speaks Cohere, Jina and Voyage request shapes and scores each document with a Jev relevance question.

Python library that reranks RAG results and filters out documents that do not help answer the query, using Jev Noul judgments.

Self-hosted MCP research server that filters search results and page blocks with Jev, returning compact evidence with provenance.

Spring WebFlux starter: a semantic circuit breaker where Jev flags HTTP 200 responses whose bodies actually encode failures.

Configurable GitHub Action where Jev reviews catalog submissions or classifies PRs under a JSON policy and updates one templated comment.

Browser-based systematic-review extraction tool where Jev points at the lines that answer each question and code copies verbatim quotes.

Async Python intent and tool router: Jev picks the handler, and a code-side confidence gate stops weak or invented decisions.

Router that uses Jev's cloud decisions today, logs every decision with probabilities, and distils a local routing model from your traffic.

Local pass-through proxy for Claude Code and Codex where Jev picks a model tier per human turn and only moves up within a session.

TypeScript npm router that picks the cheapest of two or three model tiers able to handle a query, using one Jev classification.

Claude Code plugin where Jev asks one yes/no per standing rule and delivers only the rules relevant to each prompt, once per session.

Ring Zero: kernel-level runtime security for AI agents, with Jev as an optional check that can only raise severity, never permit.

MCP server that scores every search query, result and fetched page an agent sees for relevance, credibility and steering risk.

Title and abstract screening for systematic reviews with Jev: include, exclude or maybe per record, with reasons, PRISMA counts and recall.

Claude Code hook that blocks known key formats locally and sends unknown high-entropy strings to Jev only in masked form.

Reviews agent skills, MCP configs and source with local static checks plus Jev before install, reporting evidence, risk and coverage gaps.

sys1grep: a zero-dependency grep that finds lines by meaning, scoring each line with Jev, with AND/OR/NOT and cross-language queries.

Site audit for SEO and AI-search visibility: a deterministic crawl, narrow Jev Choice, Score and Noul questions, and a live dashboard.

Google Sheets custom functions JEV_IF, JEV_PROB, JEV_CHOICE and JEV_SCORE that classify, tag and score cells with Jev.

Semantic MCP firewall that screens tool calls, results and descriptions with Jev, plus allowlists and session taint tracking.

Chrome extension that uses Jev to spot native ads and sponsored feed cards, alongside network and media ad blocking.