Platformization’s HackerNoon roundup collects 101 examples of people using Jev for bounded decisions. This directory condenses that list into categories with direct project links, so it is easier to find an implementation worth exploring.

What is counted: 101 source entries, including 91 distinct GitHub repositories. The remaining entries include demos, articles, social posts, a package listing, and a non-GitHub repository. These are not 101 independently tested tools.

Evidence status: the descriptions below report the roundup’s use cases. The individual implementations have not been audited or run for this directory. A listing is a research lead, not a recommendation; performance claims need their own checks.

For a closer look at one additional implementation, see Call Coach AI: typed decisions during a live sales call. For background, see Diogo Almeida on what comes after RLHF.

Classification & Routing

  • 1. Notra — A production generative-engine-optimization platform that moved its brand-visibility classifiers off an LLM and onto Jev Boolean decisions behind a feature flag, targeting 300ms p50.

  • 2. jev-router — Routes each Claude Code task to the cheapest model actually capable of handling it, using a Jev Choice over candidate models.

  • 3. jev-router (prismhq) — An open-source LiteLLM-based router where a Jev decision picks the serving model per request.

  • 4. pi-jev-router — Adds per-request model routing to the Pi coding agent over Vercel AI Gateway.

  • 5. jcm-router — A local proxy that picks both the Claude model and the reasoning effort for each message, while leaving the cached main chat untouched.

  • 6. jev-agent-skill-router — Routes agent skill selection through confidence-aware Jev decisions, so a weak match is declined rather than guessed at.

  • 7. typesafe-jev CV screener — Screens a folder of CVs against an editable policy using typed judgments, and re-scores every candidate for free when the policy changes.

  • 8. Jev email intent workflow — An async LangGraph workflow that takes a Jev Choice between invoice and general and routes inbound mail to the right handler.

  • 9. unclutter — A browser extension where Jev decides, per page element, whether it’s clutter, then strips it under reusable template rules.

  • 10. typesafe-adblock — A Chrome extension that asks Jev whether each DOM element is an ad, turning ad blocking into a stream of per-element typed questions.

  • 11. DiffJury — Triages pull requests by risk before assigning a human reviewer, and doubles as a review coach.

  • 12. HA-Jev — A Home Assistant integration that answers questions about the house as a probability, a choice, or a score.

  • 13. secondlayer — A self-hosted Stacks blockchain data service that runs both its Slack gate and its fault-triage path on Jev decisions.

  • 14. new-api-typesafe-plugin — Adds a native /v1/systemone endpoint to the new-api gateway so typed decisions sit behind the same infrastructure as chat models.

  • 15. json-render — Vercel Labs’ generative UI framework uses Jev in its compose path to pick which components and actions a rendered interface should contain.

  • 16. hono-jev-router — Hono middleware that routes HTTP requests by what they mean rather than by method and path.

Verification & Guardrails

  • 17. is-malicious — Asks Jev Noul questions about source and build files, escalates suspicious chunks for a second pass, and reports the implicated files and line numbers before anything executes.

  • 18. jev-review — A staged code-review workflow with a local dashboard, where Jev gates each stage before a change advances.

  • 19. pi-jev — Adds a measured tool-call gate to the Pi coding agent so risky calls get checked before execution.

  • 20. OpenWork — Wires Jev into its eval testkit as a verification judge, so agent-produced work is gated by typed verdicts instead of a text model’s opinion.

  • 21. jev-guard — A prompt-injection and dangerous-action guard covering Claude Code, Codex, Pi, and ACP agents, with Jev deciding what to block.

  • 22. Foreman — Sits above Codex workers and has Jev independently judge whether an implementation is complete, whether its tests are sufficient, or whether a human is needed.

  • 23. opencompany — Runs its approval review through Jev so workspace actions are gated by a typed decision.

  • 24. jev-git — A sub-second pre-commit and pre-push gate that screens staged diffs for secrets and destructive commands.

  • 25. pi-heed — Checks every side-effecting tool call from the Pi agent against what the user actually asked for.

  • 26. Hunch — Plain-English rules that Jev checks code against, locally or on every PR, picking one label per finding.

  • 27. Abide — Reads every edit a coding agent makes and flags rule violations.

  • 28. fx — Ships a typesafe_permission_reviewer builtin so the coding agent’s permission decisions run through Jev rather than another LLM call.

  • 29. Sniff Test — A prose linter that asks Jev ten Boolean questions per paragraph (stacked hedges, restating closers, naked cost figures) at a 0.7 threshold, shipped as a CLI, pre-commit hook, GitHub Action and Claude Code skill.

  • 30. jev-pref — Turns the preferences written in a project’s AGENTS.md into machine-checkable rules that Jev evaluates against each diff hunk or PR, returning fix_now or advisory findings and a nonzero exit code on blockers.

  • 31. jev-judgment — An agent skill that sends closed coding-agent judgments to Jev so verdicts stay typed, cheap, and comparable across runs.

  • 32. limpet — A Stop hook that keeps an agent from declaring victory early by judging plain-language completion rules.

  • 33. jev-mcp (jkudish) — A proof-of-concept MCP server putting Jev claim verification, content screening, and candidate ranking behind standard MCP tools.

  • 34. jev-mcp (blakestone-x) — Exposes classify, score, check, match, and screen as MCP tools with confidence on every answer.

Scoring & Ranking

  • 35. Clean Code Judge — Scores every file in a PR against 31 boolean Clean Code smells plus function size and nesting, then passes the verdicts to a writing model for the prose.

  • 36. citation-verifier — Checks whether each cited paper actually supports the sentence citing it, with Claude locating the quote, Jev scoring the support, and a human making the call.

  • 37. jev-bfs — Finds link paths between Wikipedia articles by having Jev rank each page’s outgoing links while Python runs the search.

  • 38. Jev Search — Reranks Search1API results using Noul judgments on titles and snippets, with application code merging duplicate URLs and grouping weaker matches separately.

  • 39. pagegrade — Grades page sections for clarity, writing quality, and on-page SEO, returning per-section scores.

  • 40. jev-scout — A repo and crate scout using speculative fan-out scoring to vet open-source packages in under a second.

  • 41. jev-seo — A zero-cost SEO and generative-engine-optimization radar CLI and MCP server built on DuckDuckGo plus Jev scoring.

  • 42. JevSlop — Scores note.com articles on eight Score axes inside one request and converts them to a 0-100 slop score in ordinary TypeScript.

  • 43. SemanticSpace — Places phrases in 2D by asking Jev how strongly each relates to two chosen axis concepts, using the scores as coordinates.

  • 44. LlamaIndex Jev — An unofficial adapter where Jev scores each retrieved passage and selects the query engine.

  • 45. typeful-triage — A multiplayer triage dashboard where Jev answers a fixed set of typed questions per issue — kind, severity, urgency, duplicate, next step — and every human correction is retained and shown back on later runs.

  • 46. jev-curate — Sifts synthetic JSONL and Parquet rows using Noul checks and calibrated confidence, streaming passes and rejections straight to disk.

Agent Decisions

  • 47. Jev Ultrafast — browser-use’s ultrafast agent, where Jev decides each next action and element to click and a language model is called only when text must be typed.

  • 48. Jev Browser — Drives a browser with Jev deciding each step, executing through Playwright, and careful handling of irreversible actions.

  • 49. fastbrowse — Jev picks each action from what’s on the page while the LLM reads and plans.

  • 50. public-browser — Lets Claude Code and Cursor drive a real Chrome profile with a Jev loop choosing actions, reporting roughly 30% fewer tokens and 25% lower cost.

  • 51. Stagehand + Jev — Sends the accessibility tree as state and candidate actions as questions, so Jev decides each step.

  • 52. pi-typesafe-jev — Exposes System One judgments as five Pi tools, so the model makes narrow semantic judgments while code and users keep control of thresholds, weights, and actions.

  • 53. pi-quiet-ask — Gives the Pi agent a quiet decision layer for judgments it would otherwise hand to a chat model.

  • 54. dsh-auto-mode — A DeepSeek Harness permission preset that has Jev answer the open questions an agent leaves in its final message, steering them back only when a Choice clears 0.6 confidence and a safety Noul clears 0.5, and handing back to the human otherwise.

  • 55. augustus — An agent skill mapping Choice, Score, and Noul onto classical methods, with a composition algebra, question-design diagnosis, and a validation gate requiring a falsifying experiment.

  • 56. yoshi — A proxy for Claude Code and Codex where Jev judges which conversation history is still needed before pruning.

  • 57. fast-jev-compaction — A Claude Code plugin that replaces the compaction summary entirely, scoring each tool call and result for whether it’s still needed rather than rewriting the session.

  • 58. pi-fast-jev-compaction — Same idea for Pi: preserve conversation text exactly, prune stale tool history, and fall back to native summarization only when pruning can’t free enough room.

  • 59. Atomic — A coding agent runtime shipping a first-class Jev structured-output provider, so agent decisions come back typed through the same resolver as every other provider.

  • 60. robo-harness — An SO-101 robot arm workbench where a Jev decision runner picks bounded joint steps from typed candidate actions under a spend budget.

  • 61. jev-superpowers — A systematic development framework for coding agents with typed decisions, zero-hallucination package vetting, and completion gates.

  • 62. Jevbridge — An ACP and MCP adapter exposing typed decisions to Codex, Claude, Grok, and others.

  • 63. Smithers — A TypeScript workflow framework with a Jev session checker wired into its workflows.

  • 64. skillbox — A self-hosted, versioned skills library that adds optional Jev-driven skill recommendations using your own key.

  • 65. typesafe-ai/skills — The official installable agent skills package that teaches agents the Jev workflow, via npx skills add typesafe-ai/skills.

Coding, Eval & Data Infrastructure

  • 66. eve — Vercel’s eve engine ships Jev as the default evaluation model in its experimental evaluate path.

  • 67. AI CLI — Vercel Labs’ CLI can run Jev as the model behind its evaluate command.

  • 68. ai-python — The official Vercel AI SDK for Python carries Jev through its evaluation operation and Gateway examples.

  • 69. Cline plugins — Cline’s official plugin collection includes a Jev-driven browser plugin, making Jev a first-class capability rather than a community hack.

  • 70. rotom — An OpenAI- and Anthropic-compatible local gateway carrying Jev through its model catalog and evaluation path.

  • 71. safer-with-jev — A Neon Function proxy for the Neon AI Gateway that routes decisions through Jev.

  • 72. jevql — A psql-shaped CLI with Go, TypeScript and Python SDKs that runs plain SQL against vanilla Postgres, then asks typed questions about each surviving row so you can apply jev() filters, jev_prob sorts, and jev_choice groups.

  • 73. sqlite-jev — A loadable C extension and Python package exposing Noul, Choice, and Score as SQL functions and batched virtual-table queries with confidence results.

  • 74. jev() for PostgreSQL — A single SQL function that searches a whole database in natural language with no index and no embeddings, as in WHERE jev(people, 'could work from home').

  • 75. DuckDB row classification — Classifies rows in any CSV, Parquet, or DuckDB table, reported at about ten seconds per thousand rows with better ergonomics than a bespoke classifier.

  • 76. advocaat — A small type-safe client for asking questions about a dataset.

  • 77. zio-typesafe-ai — A ZIO client for Scala with a typed DSL over Jev decisions.

  • 78. TypeSafe AI Swift SDK — A dependency-free Swift 6 client with strict concurrency, configurable auth and retries, and offline transport tests.

  • 79. laravel-typesafe-jev — An unofficial Laravel integration with typed responses, async requests, scoped DI, and testing fakes.

  • 80. jev (Elixir) — A GenServer client that replies with the answer so callers can pattern match on it directly.

  • 81. jev-go — A community Go SDK.

  • 82. jevclient — An async Python client on PyPI.

  • 83. jev-cli — A small dependency-free CLI.

  • 84. decide-mcp — A configurable decision server with percentage scores and bias-profile routing layered on Jev.

  • 85. typesafe-jev-examples — Worked ticket-triage and reranking examples runnable through OpenRouter without an early-access key, with sample data and a Makefile.

  • 86. Jev AI — A public playground and API for putting Choice, Score and yes/no questions to the model about pasted text, returning a parsed answer with confidence in about half a second.

Evaluation & Benchmarking

  • 87. jevcal — Fits a per-question confidence threshold to a target accuracy on your own labeled data, verifies on a held-out split, reports how much traffic still has to escalate to an LLM, and fails CI when a model update breaks the locked thresholds.

  • 88. Jev Playground — Benchmarks Jev against Luna, Haiku, and Gemini at choosing validated legal moves in explicit-state games, scoring decision quality and consistency over a move sequence.

  • 89. Jev vs Mistral and Gemini for event validation — A head-to-head on validating local event listings against Mistral Small and Gemini Flash-Lite.

  • 90. Judge call vs dimension scores — Tests one direct question per row against 12-14 scored dimensions with locally fitted weights, reaching 0.9076 against 0.8373 on Japanese NLI but flagging roughly 25× more hard benign rows as attacks.

  • 91. Jev Pong — Pong where the ball advances one step per model decision, putting Jev head-to-head with LLMs through Vercel AI Gateway.

  • 92. minutes — A local-first transcription app running its live voice-path evaluations through Jev.

Games, Simulation & Robotics

  • 93. typesafe-mario — Plays Super Mario Bros. from structured emulator state, choosing each action from emulator-derived features.

  • 94. jev-plays-pokemon — Reads Pokémon Red state as text, answers typed questions each turn, and lets deterministic code turn answers into moves.

  • 95. tsai-sc — Drives original StarCraft shareware through keyboard and mouse, recording action probabilities per decision.

  • 96. jev-drone — A camera-only autonomous drone in MuJoCo with a Jev judgment model in the control loop at 2.5Hz.

  • 97. typesafe-jev-drone-demo — A Three.js drone simulator with a Python backend where Jev makes the navigation decisions.

Finance, Legal & Moderation

  • 98. jev-trade — Asks for a long-or-short Choice on a Hyperliquid market each round, places the order, and runs the same loop across many assets.

  • 99. On-chain trading on Monad — Jev decides buy or sell from a live price feed and the bot places real orders every 300ms block.

  • 100. LegalForecast-MTD — A benchmark asking Jev to predict federal motion-to-dismiss rulings from the judge’s written record, scored with claim-defendant micro-Brier metrics.

  • 101. mastra-jev-moderation — A Mastra input processor asking a Boolean “must this be blocked?” plus a category Choice in one request, aborting at 0.7 and failing open behind a deadline and circuit breaker.

Where to start—and what not to assume

The useful recurring architecture is narrow judgment in the model, policy and execution in ordinary code. The examples cover choosing a route, ranking candidates, checking a rule, or selecting a bounded action—not replacing every part of an application with a chat agent.

Before adopting a project, look for a real Jev API call, runnable tests, a license, explicit handling of uncertainty, and a way to measure results on your own data. Type-correct answers can still be wrong. A model-based guard is not a replacement for access controls or approval of destructive actions.

The original article also links a useful counterexample: jev-search-rerank-eval. It reports that standalone Jev reranking did not beat a good embedding ranker, although combining approaches helped. That evaluation has not been reproduced here; it is worth keeping alongside the positive demos.

The broader awesome-jev index explicitly warns that inclusion is not a code-quality or security endorsement. Treat this directory the same way.