Browser agent where Jev picks each operation and element.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: unclear
Showing 410 of 410
Claude Code plugin that prunes context with Jev instead of summarizing.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
A 0.6B parallel decision model returning full probability distributions.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
Agent skills for building with TypeSafe's System One API
Agent Decisions★ 1,240
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Trainable Jev-like decision models on Qwen3.5 you can run yourself.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Train a small model to score text options in one pass.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
macOS computer use via OCR and bounded Jev action selection.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: no
- Runnable: yes
Software factory foreman using Jev to supervise coding workers.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Staged code-review workflow with a local dashboard, gated by Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Turn open models into typed classifiers without a trained head.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Curated list of TypeSafe, System One, and Jev resources.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
22 latency-focused Jev demo apps built by Devin
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
Plain-language web search ranked by Jev relevance judgments.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev-based classifier for IRS tax document pages.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Jev picks NES controller inputs for Super Mario Bros. from structured state.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Android agent where Jev picks every action from live device state.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Curated list of projects built with Jev, TypeSafe AI's System One model.
Other★ 273
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: no
Jev drives browser controls; Codex types and verifies.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Route Claude Code and Codex turns to the cheapest capable model via Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Ask Postgres tables plain-language questions with calibrated probabilities.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Build calibrated AI Functions from human feedback using Jev and GEPA.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Open-source non-autoregressive System One decision model for calibrated inference.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev-compatible HTTP API served by Qwen3.6-35B-A3B on SGLang.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Open, Jev-compatible System One decision server on DiffusionGemma.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Calibrated 151M non-autoregressive decision engine for typed software workflows.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Enforce project rules on every coding agent edit with Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Fast, cheap browser automation with Jev picking each step.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Local MCP server giving coding agents Jev quality scores.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
A source-backed directory of open-source projects built with TypeSafe Jev.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Educational MLX vision-language inference with shared image context and direct candidate scoring.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Voice control for a real browser, deciding intent and target with Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Typed Jev judgments as MCP tools for agents.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Semantic code linting with Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
One-pass typed decisions with calibrated probabilities, no text generation.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
WXT browser extension that removes page clutter using Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
MCP server giving AI agents typed Jev decisions over stdio.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Three.js driving simulator with Jev-powered autopilot
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Claude Code plugin trims long Bash output with Jev before the model sees it.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Agent skill for writing and improving programs that call Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
TypeSafe Jev as a decision layer for the Pi coding agent.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Grep by meaning across languages using Jev probabilities.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Jev-powered router for models, tools, and subagents.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Pi guardrails that steer the agent instead of interrupting you.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Bounded TypeSafe Jev workflows for coding agents.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Compares LLM tool selection with Jev routing in a 100-tool agent.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: no
Rust CLI ranking agent skills for the next step with Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Per-turn Codex model, reasoning, and speed-mode routing via Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Document classification and splitting with Jev, LiteParse, and optional LlamaParse.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Camera-only MuJoCo drone with Jev judgment model in the loop
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Type-safe client for asking Jev questions about your data.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
A tiny decision model: state plus typed questions, calibrated probabilities.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
PostgreSQL extension calling TypeSafe AI (Jev) from SQL for classification.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Code quality and coverage for coding agents
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Skip YouTube sponsor reads with Jev-typed questions
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Live Jev BS meter over any video, rendered as a 16:9 edit.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Fish-style zsh history autosuggestions ranked by Jev.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: no
- Runnable: yes
One-pass option scoring with local Gemma 3 4B on Apple silicon via MLX.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Curated list of Jev projects, SDKs, tools, and learning resources.
Other★ 70
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: no
Cheap Jev decision layer for Grok Bot before expensive work.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Chrome extension asks Jev if each DOM element is an ad
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Quota-aware CLI routing of coding tasks to AI agents.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Semantic grep: describe it, find it, powered by Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Live Jev trader on Hyperliquid
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Parallel constrained decisions for MLX models on Apple Silicon.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Non-autoregressive decision engine with calibrated uncertainty and WebGPU playground.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Bounded Jev action selection inside Codex Computer Use
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Chrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Semantic router for Hono that routes requests by meaning with Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Paint images by having Jev predict each pixel's colour.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Discord moderation bot using Jev to score spam, phishing, and social engineering.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Open-source System One model: typed, calibrated decisions from any open-weights LLM.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Ask your house a question, get a number back.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Describe a startup idea; Jev decides KILL, FIX, or SHIP.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Reading option-letter logits instead of generating JSON on a frozen Qwen3-4B.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Curated Chinese list of Jev resources, SDKs, apps, and guides.
- Jev-centric: unclear
- Measured: unclear
- Handles uncertainty: no
- Runnable: no
Local stdio MCP server giving Cursor and Codex typed Jev judgments.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Calibrated context sieve that judges tool results before they enter Claude Code context.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
ACP/MCP adapter bridging TypeSafe Jev typed decisions with any LLM.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Classify Git commits with Jev: change types, bug and security fixes.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Reproduction of Jev: turn any Qwen model into a fast decision model.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev-guided walkers search a codebase for a natural-language query.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev picks each social research step; socai runs it in your browser.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Bounded installed-skill recommendations with TypeSafe Jev.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: unclear
- Runnable: yes
Browser agent where Jev picks actions and an LLM plans and reads.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Read-only Gmail triage with Jev probabilities, sorted locally.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Typed calibrated decisions from hidden states, zero output tokens.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Prose linter that flags AI writing tells using countable rules and Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: yes
- Runnable: yes
Local bilingual probability decisions from context, questions, and candidates.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
Curated list of TypeSafe AI Jev demos, repos, limits and examples.
Other★ 22
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Zero-cost SEO & GEO radar CLI and MCP server for developers and agents.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
TypeSafe decisions for Pi: batched evaluation, playground, typed API.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
TypeSafe Jev for OTP: GenServer replies with Jev's answer for pattern matching.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Semantic tool routing and typed System One decisions for Pi coding agent.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Local context-pruning proxy for Claude Code and Codex.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
TypeSafe Jev plays original StarCraft shareware mission Strongarm.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Jev picks one legal Snake move per tick.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Scan a codebase for malicious behavior with TypeSafe Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Independent tracker of the Jev ecosystem with verified cases.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
TypeSafe provider for RubyLLM 2 with typed, probabilistic answers.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
DuckDB extension: typed Jev answers as real SQL types
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Agent-ergonomic CLI for TypeSafe's Jev calibrated judgments.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Claude Code Stop hook that blocks unverified "done" claims.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: yes
- Runnable: yes
MCP server exposing Jev typed judgments as tools for any agent.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Auto mode security guard for coding agents, powered by Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Stock decision terminal using Jev for probabilistic 30-day outlook.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev decision layer for agents: MCP tools, library, Claude Code hooks.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Pareto-optimal OpenRouter model router for pi, based on Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: unclear
- Runnable: yes
0.8B vision-language model plays ten browser games from raw pixels
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: yes
- Runnable: unclear
Probabilistic control flow for Ruby, powered by TypeSafe's Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Peer-to-peer multi-agent runtime with zero-trust credentials and durable state.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Typed AI judgments from the command line, powered by TypeSafe's Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: unclear
- Runnable: yes
One-pass scorer over changing text options, stronger than jevlike.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Multi-drone lab: Jev reflex decisions with optional System 2 strategy.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: unclear
grep where the pattern is a plain-English description.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: no
- Runnable: yes
Experimental Jev framework forecasting Hong Kong stock direction from market state.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
Typed, confidence-aware agent skill routing with TypeSafe Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Classify your inbox with Jev — tag, move, flag, notify.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Systematic agentic skills with TypeSafe Jev typed decisions.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Interactive experiments with TypeSafe Jev for routing and driving decisions.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Jev-powered smart command approvals for Hermes Agent.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
A Chrome extension that filters live Twitch chat with Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Chrome extension driving your tab with TypeSafe Jev decisions.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Hand text-free agent steps to Jev as typed judgments.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: yes
- Runnable: yes
Prompt-first symbolic-music studio where Jev decides every musical unit.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Typed Rust client for TypeSafe's System One evaluation API.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Flue agent routing with TypeSafe Jev via Cloudflare AI Gateway
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
15 runnable Node recipes for Jev decision model on OpenRouter.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: unclear
Calibrate, threshold, and drift-check typed decision models against an LLM teacher.
- Jev-centric: unclear
- Measured: yes
- Handles uncertainty: yes
- Runnable: yes
Semantic SQL for vanilla Postgres, powered by Jev
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Semantic grep CLI that finds code by behavior using TypeSafe Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: yes
- Runnable: yes
Jev picks a Pi model and effort, then pins them.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
TypeSafe Jev as the pi coding agent's quiet decision layer.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Pre-commit hook: one Jev call judges commit message vs diff.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Score OpenTelemetry logs before expensive LLM analysis.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Sort lines by a plain-English criterion using Jev pairwise comparisons.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Typed semantic decisions for Unix pipelines and CI, powered by Jev.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: unclear
- Runnable: yes
Chrome extension labels X posts with Jev and hides unwanted ones.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Clean Code review of every PR file, judged by Jev, written by Luna.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Observable browser stealth game where Jev judges, deterministic code owns the world.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Dependency-free CLI and MCP server for TypeSafe Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
RuneBench harness for TypeSafe's Jev to play RuneScape.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Open recipe for Jev-style decision models: task description to calibrated probabilities.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Decision harness: turns Jev answers into bounded actions.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Zod validates shape; Jev validates meaning.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Aside agents decide with TypeSafe Jev (System One: Choice/Score/Noul).
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Curated list of projects that actually call Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Bounded browser agents: Jev picks typed actions, agent-browser executes.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: yes
- Runnable: yes
Design and evaluate TypeSafe Jev decision loops.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Typed Haskell DSL for TypeSafe Jev judgment packets.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Reproducible early-access check of Jev on Korean and medical text.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Pi extension pruning stale tool history with TypeSafe Jev decisions.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Scala 3 client for Jev's typed questions, no effect system.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Async LangGraph workflow routes emails via Jev Choice.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Design judgment for placing typed probabilistic judgment in software.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Rust sifter for synthetic and pretraining datasets using Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev-powered relevance filtering and reranking for RAG in Python.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Runtime constraints that check every side-effecting pi tool call.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Chrome automation MCP server with local Jev semantic micro-loop.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev routes PR risk before human review.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Pokemon Red on PyBoy: code owns the route, Jev picks at branches.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Turn AGENTS.md preferences into a fast, Jev-powered AI linter.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Semantic verification engine for AI code and specs, powered by Jev.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Cache-neutral context trimming for pi, powered by TypeSafe Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: unclear
- Runnable: yes
Neon Function proxy that routes AI Gateway decisions with TypeSafe Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Voice-driven semantic auto-advance for Slidev, powered by Cloudflare Agents and Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Catch AI slop in UI, copy, and agent instructions before ship.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Unofficial Swift 6 client for the TypeSafe AI API
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev decision primitives as a Cordis plugin suite for DeepSeek Harness.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Ask a yes/no question of every function; ranked probabilities in seconds.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Codex plugin: verbatim Jev-guided context restoration around session compaction.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Unofficial TypeSafe Jev showcase: System One decisions, not chat.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Independent behavior study of Jev 1.13.0: findings and failures.
- Jev-centric: unclear
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Open stack for training and serving Jev-style decision models.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Community Go SDK for TypeSafe AI Jev / System One.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Send closed coding-agent judgments to TypeSafe Jev
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Local Jev-compatible evaluation server with typed questions and open weights.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Independent calibration test of Jev on unseen rule-based tasks.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: yes
- Runnable: no
Jev picks Pokémon Red goals; code presses buttons.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
YouTube sponsor skipper using Jev to score captions at watch time.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Ask the buffer a question; functions ranked by probability in quickfix.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Control Android over ADB with Jev-typed decisions.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Level-40 Pokémon agent using Jev for battle decisions on real FireRed.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
SQL with natural-language predicates, powered by TypeSafe's Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: unclear
- Runnable: yes
Source-linked evidence selection within a token budget using Jev Noul relevance.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
LlamaIndex reranker and router using TypeSafe Jev typed decisions.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Binary approval gate for Claude Code, reviewed by TypeSafe Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Local, open-source Jev alternative with calibrated confidence.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: no
- Runnable: yes
Screen a folder of CVs with typed Jev judgments.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Community Java 17 client for TypeSafe System One typed questions.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Scala 3 / ZIO client for TypeSafe AI's Jev typed-question API.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Runtime authorization gateway for AI agent tool calls using Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Multi-axis writing quality checker powered by TypeSafe AI's Jev model.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Drop-in profanity and toxicity screener for Node.js, powered by Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Measure where to route between Jev and a frontier model.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Local proxy picks Claude model and effort per message with Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Per-call Codex GPT routing via TypeSafe Jev, with independent task verification.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
Voice and finger drawing on tldraw canvas with Jev decisions.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: no
- Runnable: yes
Jev classifies cloud service names with probabilities.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Sub-second Git hook screening staged diffs with Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Durable Android agent using Jev for per-step action choices.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Natural-language grep for code, docs, logs, and text.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: unclear
- Runnable: yes
Jev gates patent drafting: 300ms fact check before LLM writing.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Rerank, filter, and compress JSON search results with Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Reproducible eval harness for Jev Ultrafast research-browser tasks.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: no
Zero-hallucination repo and crate scout scored by TypeSafe AI Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Recursive Jev choice over taxonomies larger than 255 options.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Batch typed judgements over text queues with TypeSafe's Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
See what Jev thinks about your SaaS website.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
Async Python client for TypeSafe Jev typed questions.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Rust CLI for TypeSafe Jev: typed decisions, offline linting.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Record linkage with plain-English match rules and Jev probabilities.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Unofficial Laravel integration for TypeSafe Jev with typed responses and testing fakes.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Mastra input moderation on Jev: one file, one typed request.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: yes
- Runnable: yes
TypeSafe AI System One task plugin for new-api gateway.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Sticky cheap OpenCode parent; Jev escalates hard turns to subagents.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Grades page sections for clarity, writing and on-page SEO.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Reversible context pruning for Pi, powered by TypeSafe Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Batched natural-language judgments for SQLite via TypeSafe Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Policy-bounded model routing for TypeScript and Python.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: unclear
- Runnable: yes
.NET SDK for TypeSafe AI's typed judgment API.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
TypeSafe System One questions as DuckDB LATERAL-joinable table functions.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Classify files with a decision-making AI model and sort them into category folders.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Curated list of projects built on Jev, judged by Jev itself.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Unofficial list of projects using TypeSafe AI Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
TypeSafe Jev semantic guardrails for Claude Code tool execution.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Automated friction logs for documentation, scored section by section with TypeSafe Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Semantic code review with Jev, plain-English rules and Agent Skills.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Independent JEV benchmarks on MetaTool, When2Call, and BFCL V4.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Tool-call safety gate for AI coding agents, backed by Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Benchmark TypeSafe Jev against any OpenRouter model on labelled classification data.
- Jev-centric: unclear
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Universal figure and diagram router for AI agents, powered by TypeSafe Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Independent lab for Jev: benchmarks, use cases, and ecosystem audit.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Open lab for correct Jev routing in front of Claude Code.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: unclear
- Runnable: no
Jev decides if a batch of logs is worth acting on.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Eval-first MCP server for Jev's typed judgments with probabilities.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Go MCP gateway to TypeSafe's Jev model
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Automates TypeSafe (Jev) account registration and API key creation via pure HTTP.
- Jev-centric: unclear
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Neovim intent router classifying AI commands with Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Tetris played by a judgment model that cannot write or see.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Multiplayer triage dashboard where Jev answers typed questions per issue.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev docs and best practices for engineering teams
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Jevlike edge router on ESP32
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Native R client for Jev System One decisions
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Scores note.com articles for AI slop using Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Stop hook that keeps coding agents from stopping too early.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: no
- Runnable: yes
n8n community node for TypeSafe Jev structured AI decisions
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Pi extension: TypeSafe Jev judgments as five pi tools.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
SO-101 robot-arm workbench with a Jev decision runner for bounded joint steps.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Rule-based slop grader for text files, powered by Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev hosts a bilingual lateral-thinking puzzle site.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Worked Jev examples: ticket triage and re-ranking, runnable via OpenRouter.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
MCP server exposing TypeSafe Jev as a typed evaluate tool.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Ruby client for Jev: typed, probabilistic answers from application state.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Independent, source-linked research on TypeSafe AI's Jev and its ecosystem.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
AI music video director with beat-synced full-motion generation.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Community patterns and top builds for Jev, TypeSafe AI's System One model.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Ten approvals to win, judged by a probability, not a sentence.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: unclear
- Runnable: unclear
Jev-compatible System One decision endpoint over a local LLM.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Local MCP server delegating decisions to configurable models with percentage scores.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Judgment API: TypeSafe Jev on Cloudflare Workers for triage, urgency, spam, tone, risk.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: no
- Runnable: yes
Open protocol for decision-based AI agents with Jev-first orchestration.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Classify an artist's discography by theme, mood, and lyrical complexity with Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Pre-execution safety valve for DeepSeek Harness shell commands.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Flappy Bird played by Jev: one yes/no question per frame.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Local open-source drop-in for TypeSafe AI Jev with WebMCP bridge.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
GitHub Action that judges agent-written PRs and posts one comment.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
grep for meaning: a Unix CLI that searches by description.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Hermes Agent plugin exposing TypeSafe AI Jev for structured evaluation.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Home Assistant conversation integration using Jev for fast intent routing.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Independent, pre-registered evaluation of TypeSafe AI's Jev model.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Offload agent classify, screen, score, and verify calls to Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Two Jev-powered web demos: tone analyzer and maze runner.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Rank repo files by task relevance with Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Agent-ergonomic CLI for TypeSafe Jev typed judgments
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Does the cited source actually say it? A 42-claim benchmark.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: no
Wikipedia link races ranked by Jev, shown live in your terminal.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Windows Chrome/Edge browser agent using Jev for ultrafast tab control.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Two AI models play chess: one picks, one writes.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
Jev gate checks whether AI answers are grounded in cited ordinance articles.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Crypto screening: quant signals in code, news judgment via Jev.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Hands-on Jev study: concepts, 5 runnable demos, reproducible benchmarks.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: no
- Runnable: no
Framework for building agents on TypeSafe Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Calibration and selective-risk benchmarks for Jev decisions in DSPy workflows.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Benchmark and one-step RL environment for typed decision models.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Layered AI content moderation workflow powered by TypeSafe/Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Cheap fail-open semantic edge layer for Jev decisions.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Safety gate for AI coding agents, backed by TypeSafe's Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Guess your girlfriend's real thoughts with Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
TypeSafe Jev integrations for agent harnesses, CI, CLIs, and editors.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Benchmarking Jev on 5,000 CDC heart-risk survey respondents.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Chinese introduction to Jev: System One, State, Choice, Score, Noul.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: no
Jev as quizmaster for lateral thinking puzzles
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Free local Jev-compatible typed decisions with rules or Laya.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Testing Jev's typed judgments on map layer importance
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
Measured cost, latency, and raw output from the live Jev API across eight use cases.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Lightweight .NET client for TypeSafe AI's Jev probability API.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Independent measurement of whether ORDER BY over Jev probabilities is defensible.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Semantic command palette ranked by intent with TypeSafe Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: unclear
Jev as decision engine for BTC/ETH paper trading, evaluated every 5 seconds.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: no
- Runnable: yes
Jev picks enum labels; code renders sheet, audio and MIDI.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Local browser playground for Jev decision model via OpenRouter.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Structured, probability-bearing judgments from Jev, with raw HTTP transparency.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev-scored observable web research for MCP agents
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Zero-shot spam filtering with Jev Noul questions, benchmarked against TF-IDF.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Korean study notes and TypeScript mockups for Jev's typed decisions
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Reads clinical note, nudges for orders committed but not charted.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Case study on Jev's typed evaluation collapse via six experiments
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: no
Voice control for your browser using TypeSafe's Jev model.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Zero-shot benchmark: Jev vs open decision models on classification.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: no
Java SDK for TypeSafe AI: typed questions, typed answers.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Behavioral contracts for TypeSafe Jev: pin, eval, catch flips.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
TypeSafe Jev for DeepSeek Harness and MCP hosts.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Automated PR review pipeline using Jev as a millisecond decision layer.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Profanity and moderation API powered by Jev on Cloudflare Workers.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Profanity and moderation API using Jev for multi-category scoring.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
A local harness that puts Jev in front of the LLM.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
grep for meaning: find errors, commits, commands by description.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Turn any open LLM into a calibrated System One decision model.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Typed questions over your own state, not a chat.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
1,000 synthetic SaaS accounts triaged by Jev's six constrained judgments.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: unclear
Async Rust client for TypeSafe AI's Jev with typed questions and WASI transports.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
ASCII flirt game where Jev judges your pickup lines.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Interactive playground for JASM v0.2, the assembly language of JLMP.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Lightweight daily-planning assistant using Jev to evaluate tasks.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Chrome extension that filters LinkedIn feed noise with Jev and explains each verdict.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Speech-only Magic 8 Ball with Jev making bounded decisions.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
Forward an email, get a calibrated phishing verdict.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
NeonHop 3D: testbed for Jev-only runtime inference in a game.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
One-pass skill router that shrinks OmO's system-prompt skill catalog.
- Jev-centric: yes
- Measured: unclear
- Handles uncertainty: yes
- Runnable: yes
Open WebUI Tool that sends typed questions to Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
MCP server exposing JEV classification tools via OpenRouter.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Selective, verbatim context compaction for Pi using Jev.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
TypeSafe Jev sidecar adds pre-flight and diff-quality hazard checks to Pi.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Typed Jev decisions route Pi coding-agent requests to the right model.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Local RAG over Chinese LoL patch notes, with Jev for reranking and self-check.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: unclear
- Runnable: unclear
Coding agent with calibrated System One reflexes on top of Pi
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Fast, prefill-only decision model with typed questions and calibrated probabilities.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
Voice-controlled computer agent on TypeSafe Jev for macOS and Windows.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
Typed System One decisions for Rust via derives and confidence gates.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Label every sentence with calibrated probabilities from Jev, rendered as a heatmap.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: no
- Runnable: unclear
Jev vs six LLMs: decisions per minute and cost in Snake.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: no
Territory intelligence for a NetSuite AE, with Jev and Claude.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Benchmark catalog for Jev evidence, findings, and reproducible decision benchmarks.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Simulated fraud interceptor comparing Jev and Gemini on synthetic transactions.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: no
Community Java SDK for the TypeSafe AI System One (Jev) API.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Unofficial Rust SDK for TypeSafe AI, ported from JavaScript.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Windows desktop automation where Jev picks each operation and target.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Personal finance tracker using Jev's typed decisions for categorization and anomaly detection.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Three.js drone simulator with Python backend and live TypeSafe Jev navigation.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Community Kotlin port of TypeSafe AI's JavaScript SDK for Android and JVM.
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
PHP 8.3 SDK for TypeSafe's System One API
- Jev-centric: unclear
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Next.js UI showcasing TypeSafe's System One (Jev) model use cases.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Typed OCaml Eio client for TypeSafe AI's Jev evaluation API
- Jev-centric: yes
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Ask Jev if a sleeping agent's wakeup is worth an LLM turn.
- Jev-centric: yes
- Measured: yes
- Handles uncertainty: yes
- Runnable: yes
Chrome extension collapses low-quality X replies using local rules and TypeSafe Jev.
- Jev-centric: yes
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Educational AI hedge fund proof of concept with investor agents.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Open-source AI trading OS with Jev System One integration.
- Jev-centric: no
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Tiny, open, embeddable native coding agent CLI in Zig.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Semantic ifs from open models, on a 3090 at home.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: unclear
One AI trade decision every Monad block on Kuru MON-USDC.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Verifiable coding agent runtime with typed Jev decision provider.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Vercel Labs CLI for generation and typed evaluation with Jev.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Agentic workflow framework for TypeScript flows that instrument a code repository.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Self-hosted versioned skills library for AI agents with optional Jev recommendations.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Drop-in TypeSafeClient replacement backed by LLM APIs
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Track brand visibility in AI answers and draft content.
- Jev-centric: no
- Measured: unclear
- Handles uncertainty: yes
- Runnable: unclear
Official TypeScript/JavaScript SDK for the TypeSafe AI API.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Official Python client for the TypeSafe AI API.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
MuJoCo Franka Panda workbench for embodied AI decisions with Jev and other models.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Papers, open models and evaluations behind System One models and Jev.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Ruby client for decision models like Jev.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Side-by-side benchmark of Jev vs Qwen on structured judgment tasks.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Official curated plugins for Cline CLI and extensions.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Verbatim quote extraction for systematic reviews, verified by Jev.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Probability-aware evaluation for typed decision models: calibration, selective risk, latency.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Evidence-graded index of the Jev / TypeSafe System One ecosystem.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Evidence ledger that blocks unsupported "done" claims from AI coding agents.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Does a TypeSafe Jev rerank beat embedding search?
- Jev-centric: no
- Measured: unclear
- Handles uncertainty: no
- Runnable: no
Unofficial Chinese translation of the official Jev (TypeSafe AI) docs.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Benchmarking Jev vs dedicated rerankers on 14 datasets.
- Jev-centric: no
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Open-source LLM router where Jev picks the serving model.
- Jev-centric: no
- Measured: no
- Handles uncertainty: yes
- Runnable: yes
Check if cited papers support citing sentences.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Reward-hack radar for coding agents: structural denies plus Jev sidecar.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Community Rails integration for TypeSafe's System One API.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Curated bilingual list of Jev projects, SDKs, tutorials, and evaluations.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Directory of projects built on Jev, TypeSafe AI's System One model.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Decisions as code on System One models: typed questions, thresholds with hysteresis, nested decisions, journal, calibration
Many questions, one requestTiered thresholdsEnter / exit thresholdsDecision as codeQuestion health measured
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Issue triage that stays quiet when it isn't sure.
- Jev-centric: no
- Measured: unclear
- Handles uncertainty: yes
- Runnable: yes
Measure Jev's real capabilities before building on it.
- Jev-centric: no
- Measured: yes
- Handles uncertainty: no
- Runnable: no
Top-down traffic simulator comparing Fixed, Adaptive, and Jev signal controllers
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Jev and System One documentation extracted into markdown for LLM training.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Unofficial Go SDK for the TypeSafe v1 API.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Go client for TypeSafe's System One API with typed questions.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Experimental Swift SDK for the TypeSafe AI API.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Risk triage for large git diffs and repository-wide dead-code scan.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Coding-agent CLI where Jev decides and an LLM executes.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
A Chinese-first index of TypeSafe JEV community content.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Unofficial CPU-first System One–compatible decision server with Playwright browser agent demo.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Third-party check: Jev vs GPT-4o-mini and Claude Sonnet 4.5 on booking inquiry routing.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Jev opportunity map for Grok Bot and Grok Build builders.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Benchmarking Jev against other models in explicit-state games.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Pong where the ball advances one step per model decision.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: no
Local GMO FX/BTC market research terminal with TypeSafe Jev paper-trading integration.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
One MCP facade for multi-source scraping, normalization and Jev evaluation.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Daily arXiv paper radar scored by TypeSafe AI relevance.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
Menu-bar Mac search that finds files, apps, tabs and people by description.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
A PreToolUse hook that narrows Claude's file reads to the answering chunk.
- Jev-centric: no
- Measured: yes
- Handles uncertainty: no
- Runnable: yes
PHP SDK for TypeSafe AI: ask typed questions, get typed answers.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
CLI that decides where a task runs and dispatches it.
- Jev-centric: no
- Measured: no
- Handles uncertainty: no
- Runnable: yes
No project matches these filters.