All decision model projects

Semantic linter that checks each source file against plain-English conventions and reports Jev's probability of a violation.

Go linter that extracts code units with Tree-sitter and asks a decision model whether each passes a plain-language rule.

Python agent runtime where Jev Choice decisions pick tools and arguments, and low-confidence picks go to an LLM for review.

Google Apps Script Gmail classifier that applies your own plain-English labels with Jev and archives only high-confidence unwanted mail.

Pac-Man where Jev or other System One models choose each move at junctions, with live odds, fallbacks and a leaderboard.

Project memory for Claude Code that asks Jev whether each chat statement is worth keeping and checks tool calls against saved rules.

Zero-dependency Python toolkit of nine agent skills whose typed decisions pass a code gate and are sealed in a hash-chained ledger.

Message moderation that asks Jev for probabilities of spam, scam, harassment and other harms plus your own plain-English rules.

Local memory for coding agents that stores verbatim quotes and has Jev grade memory lines as keep, stale, wrong or unsupported.

Local OpenAI/Anthropic-compatible proxy where one Jev call picks the model route and thinking level for each coding-agent turn.

Test harness for any Jev-API decision model: accuracy, calibration and robustness probes for reordering, injection and padding.

Unix filter CLI that pipes files, lines or records to Jev for bulk yes/no, choice or score judgments so agents need not read everything.

Claude Code plugin that logs your prompts locally and later has Jev score how well you prompt the coding agent over time.

Prunes long command output for coding agents by asking Jev which lines matter for the task, keeping original text and order.

Python library that replaces hard-coded RAG thresholds with calibrated decisions for stopping, chunking, selection, abstention and caching.

Skill and plugin for Codex, Claude Code and other agents that helps them use Jev for bounded judgments and measure the effect.

Router that puts models, subagents, skills, MCP tools and CLIs in one candidate set and asks Jev one Choice about which handles the step.

Open-source desktop browser agent where a language model plans, Jev chooses the executable action and Chromium carries it out.

Mines timestamped driving scenes from vehicle logs by asking Jev lateral and longitudinal manoeuvre questions per moment.

Toolkit where Jev condenses large MCP responses for Claude Code and maps Codex requests to reviewed, fixed repository operations.

Python pre-check layer that uses Jev Choice/Noul/Score to route agent requests to roles and gate side-effecting tool calls.

Agent skill that has Jev pick the few relevant lines from big logs before your coding agent reads them, with a reversible reduce and ledger.

SQLite and Node library adding Jev judgments to SQL for matching, evidence picking, ranking, review queues and semantic CI checks.

Resume review app and MCP server where a Cloudflare Worker asks Jev typed questions and composes a JevScore, generally or per job.

Semantic test matchers for Vitest and Jest that ask Jev whether output satisfies a plain-English expectation and threshold the probability.

Plain-English end-to-end tests for Android and iOS apps where Jev works out the taps and a lockfile replays every decision exactly.

Prompt-first music studio where Jev makes every compositional choice, from plan to each bar pattern, rendered as editable MIDI.

Offline TypeScript token counter and request-cost estimator for Jev 1.13, a port of the reconstructed jevtok encoder.

MCP server that returns only the JS/TS code a task needs by following the TypeScript compiler graph and asking Jev about relevance.

Coding-agent plugin that has Jev auto-approve shell permission requests it judges harmless and abstains on anything uncertain.