Jev AgentA source-verified directory of 487 Jev projects — browser agents, model routers, SDKs and MCP servers — each one showing the exact decision it hands to Jev. Curated by the Awesome Jev community, mirrored here under MIT.
Give Jev the current state and a few options. Get the Agent’s next step.
Core call · setup in the full example
const nextStep = choice("What next?", { login: null, askUser: null, retry: null });
const { answers } = await client.systemOne({ state: "Login form is ready", questions: { nextStep } });
console.log(answers.nextStep.choice);Node.js 20+ · Set TYPESAFE_API_KEY on your server. This page shows code and makes no model requests.
A Jev UI-composition experiment inside the json-render website that selects from predefined component and property options.
Evaluates component configurations through Vercel AI Gateway, then composeSpec assembles the UI specification.
Provides an inspectable composition path alongside token-by-token JSON generation.
Creates edited videos with score meters by asking Jev to rate transcript sentences against selected rubrics.
Scores transcript sentences with preset questions and scales for meters placed on the video timeline.
Aligns sentence scores with the corresponding video segments for review.
YouTube extension detecting sponsored segments from live audio and transcripts using Jev, skipping promotional blocks automatically.
Inspects transcript segments with Jev to identify sponsor reads while browser code handles playback timeline skipping.
Identifies promotional reads on newly released videos immediately without waiting for crowdsourced segment submissions.
Requires Python 3.9+ and a modern browser with module workers and OffscreenCanvas (current Chrome, Edge, Firefox, or Safari). No packages, build step, or Node installation needed.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Shows a Jev scorecard before posting on X, assessing draft clarity, tone, and possible offensiveness.
Sends the draft and reply or quote context to Jev for multiple scores and a posting suggestion.
Collects several perspectives on a draft before it is sent.
A visual-reference gallery drawing from The Met, NASA and Cosmos, with Jev in local Explore mode.
Jev selects search phrases and highlights references using titles and descriptions, not image pixels.
Keeps source links; the public search demo does not call Jev and is not evidence of visual clustering.
A Markdown and plain-text prose linter using local rules and optional Jev judgments.
Assesses paragraphs against style rules such as redundant closings, clichés and excessive hedging.
Reports files, lines and rules while leaving revision to the author.
Turns a music prompt into editable multitrack MIDI by asking Jev to choose instruments, harmony, and bar patterns.
Selects form, instruments, chords, and rhythm candidates; local code renders the choices as notes.
Preserves editable tracks and decision receipts with playback and MIDI export.
Turns UI descriptions into selections from existing shadcn/ui components, fields and styles.
Breaks requests into choice and score questions and maps answers to a bounded component catalog.
Demonstrates UI composition through decisions; Jev itself does not generate page code or copy.
Custom nodes for using Jev's text interpretation and judgments in ComfyUI. Use natural-language instructions to select candidates, evaluate conditions, score text, or extract numbers, then pass the results to other nodes. Jev judgments use the TypeSafe API by default.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Blender exposes ~2,500 operators; a TypeSafe `Choice` question holds at most 255 options, so the search is hierarchical (two requests per search):
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Voice-driven semantic auto-advance controller for Slidev presentations powered by Cloudflare Agents and TypeSafe Jev.
Analyzes live speech transcripts with Jev to judge whether the current slide's topics are covered, triggering slide transitions.
Enables hands-free slide navigation by combining semantic completion checks with manual safety overrides.
A Game of Thrones text-adventure demo where a language model writes the story and Jev labels the scene.
Classifies location, narrative beat, mood, danger and whether text remains in fiction.
Uses explicit scene state to drive backgrounds, music and the next turn.
Explores Jev on harmony exercises and music-theory questions, alongside a piano demo driven by chord choices.
Chooses voices, pitches, durations, or chords; code grades exercises or synthesizes playback.
Puts music-theory tests and an audible composition experiment in one project.
Jev can't generate text. So I made it talk anyway. A conversational interface built from probabilistic decisions and a deterministic language compiler — no generative LLM.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
TypeSafe's `/v1/systemone` endpoint classifies text — it returns a `choice`, a `score`, or a probability. It does not generate prose. This library makes it generate prose anyway: every word of the answer is a separate `choice` question over a vocabulary, and the loop feeds its own output back in as the prefix.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
A community-maintained directory and radar for Jev, highlighting open-source projects with verified code and clear decision architectures.
Jev is TypeSafe's decision model. This directory groups projects by how they use choices, scores and probability judgements, with implementation links to help you assess fit for your own task.
TypeSafe ↗We prioritize open-source projects with clear Jev implementation evidence. Repositories without verifiable source code are excluded from the main directory.
Directory data and design from Awesome Jev by logicrw, used under the MIT License.
