All decision model projects

Jev decision layer for agents: seven MCP tools, an embeddable library and escalate-only Claude Code hooks at harness boundaries.

Browser tests written as user steps: Jev finds each control once, the path is recorded, and replays run without the model.

CLI and MCP tool that finds hard-coded judgment calls in your code, scores how well Jev fits, and replaces strong fits with a fallback.

Transparent proxy that asks Jev to classify each coding-agent prompt and injects the decision into the agent's context before it generates.

Semantic grep for code, diffs and CSV rows that packs 16 chunks per Jev request and prints file:line hits with CI-friendly exit codes.

Record linkage for researchers: write the match rule in plain English and Jev judges each candidate pair with a probability.

Assembles source-linked evidence for an AI task within a token budget using Jev relevance judgments and diversity-aware selection.

Vercel Labs' generative UI framework with an experimental compose path where Jev picks which catalog components and actions to render.

sort where the key is a description: Jev judges pairs of texts and a Bradley-Terry fit turns them into a scored ranking.

Ruby gem that stores Jev Noul, Choice and Score answers about a record's text as ordinary ActiveRecord columns you can query.

One YAML task to classify, route, score or verify text with rules, Jev, NanoJev or an OpenAI-compatible model, with cost records.

Local-first macOS coding workspace that runs your agents and lets a local Laya or hosted Jev selector pick a route the host validates.

Fast Rust terminal coding agent with 44 providers that can ask Jev for its own decisions through a bundled client.

Multi-user MCP 'agents' cloud' on Cloudflare Workers with an optional search stage that reranks candidates with Workers AI Jev scores.

Voice assistant daemon for Hyprland Linux desktops that acts through tool modules, with Jev gating which requests and actions proceed.

Middleware for LangChain deepagents where Jev ranks and verifies which SKILL.md skills each turn needs, keeping the rest out of the prompt.

Focus mode for Omarchy/Hyprland that has Jev judge each screen against your declared task and escalates gently when you drift.

Passive Chrome extension that inventories a site's browser-visible attack surface and uses local Laya or Jev to prioritise findings.

Zero-dependency npm package that runs Laya natively or as WebAssembly in Node, Bun and browsers, drop-in for Jev's /v1/systemone.

Decision middleware for AI agents that uses local Laya to pick tools and judge results, falling back to an LLM when unsure.

Native C++ Laya inference on ggml with CUDA, Vulkan and Core ML, plus a Jev-compatible HTTP server with automatic batching.

Agentic LEGO builder that turns an idea into an LDraw model, using Jev reranking to find suitable parts and example models.

Test selector that asks a judge whether a code change could affect each test, skipping only confidently irrelevant tests.

Stop hook for coding agents where Jev checks each attempted stop against plain-language rules and sends the agent back if one is violated.

Turns freeform Markdown engineering rules into PR checks, judging changed lines with Jev or other Decisions-API providers.

Single-binary linter whose rules are plain-language questions in YAML, asked of each file as a Jev yes/no judgment.

Liquid Glass voice typing for macOS 26 with an optional Jev fast path that types clean short sentences without waiting for LLM cleanup.

GitHub Action that asks Jev yes/no questions about each diff chunk for secrets, vulnerabilities, complexity and prompt injection.

Ableton Live controller where a one-sentence command in English or Japanese is turned into mixer, transport, clip and device actions.

Chrome extension that has Jev judge each LinkedIn post for engagement bait, self-promotion and relevance, hiding noise with explanations.