shipwithjev

GitHub

375 builds · page 3 of 10

  1. 0418

    World Monitor

    Geopolitical dashboard that batches Jev 1.13.0 headline-severity and topic classifications, validates the answers, and falls back when classification fails.

    koala73 · Triage & routing

  2. 0417

    typesafe-jev-workflow

    LangGraph email-intent workflow using a typed Jev choice.

    GiesN · Triage & routing

  3. 0416

    tax-doc-classifier

    Classifies text-bearing PDF pages into IRS form and page-kind candidates with a confidence gate; document triage, not tax advice, and scanned pages need OCR.

    kyotofin · Triage & routing

  4. 0415

    pg-jev

    PostgreSQL extension for semantic questions over table rows.

    realZachi · Triage & routing

  5. 0414

    neo4jev

    Navigates a Neo4j graph by having Jev score neighbouring relationships, then beam-searching for the most probable path.

    jexp · Triage & routing

  6. 0413

    n8n-nodes-typesafe-jev

    Community n8n node for asking multiple typed questions over workflow state.

    n3ndor · Triage & routing

  7. 0412

    llama-index-jev

    LlamaIndex reranker and selector using Jev Score and Choice answers, with configurable confidence handling.

    WiktorB2004 · Triage & routing

  8. 0411

    jevsql

    SQL-like filtering, ranking, classification, and scoring with natural-language predicates.

    EugeneBoondock · Triage & routing

  9. 0410

    JevMail

    Read-only Gmail triage that stores messages locally and asks Jev for bounded category, urgency, and human-sender probabilities.

    fazlerocks · Triage & routing

  10. 0409

    jevlogs

    OpenTelemetry log triage before more expensive analysis.

    reachjalil · Triage & routing

  11. 0408

    jev-tree

    Recursive choice over taxonomies larger than Jev's direct option limit.

    reachjalil · Triage & routing

  12. 0407

    jev-curate

    Streaming filter and scorer for Parquet and JSONL datasets.

    AkashPriyadarshii · Triage & routing

  13. 0406

    Jev Web Analyzer

    Fetches a public SaaS page as Markdown, then asks Jev ten bounded questions about likely first-visit comprehension; URL validation, caching, sanitization, and presentation remain…

    replynodes · Triage & routing

  14. 0405

    Inbox Zero

    Email assistant where Jev is an optional classifier backend returning bounded categories and yes/no probabilities.

    elie222 · Triage & routing

  15. 0404

    SlidePilot

    Experimental Slidev controller that judges speech transcripts for slide completion, with deterministic checks and manual navigation.

    harshil1712 · Content & growth

  16. 0403

    jevmeter

    Scores every sentence in a video and renders the result as an overlay.

    ChetasLua · Content & growth

  17. 0402

    yummy-pi-extensions

    Extensions for the Pi coding agent, each released separately, including a Jev-based model router.

    sugarforever · Tools & apps

  18. 0401

    wakegate

    Experimental gate where Jev decides whether a timer or incoming event is worth resuming a sleeping agent's LLM; code skips only when Jev is confident and always wakes on user…

    shitianfang · Tools & apps

  19. 0400

    tripwire

    Runs seven checks on every LLM response in one Jev call, as AI SDK middleware or an OpenAI-compatible proxy.

    noelzappy · Tools & apps

  20. 0399

    TanStack AI

    `@tanstack/ai-typesafe` adapter exposing typed Boolean, Choice, and Score decisions through TanStack AI's `decide()` API.

    TanStack · Tools & apps

  21. 0398

    System One Harness

    Turns a decision model into an agent loop: it compiles the environment's finite action space into typed questions, gates each step by confidence, and records the trace.

    HarnessRouter · Tools & apps

  22. 0397

    supercov

    Scores source files so coding agents can prioritize code-quality work.

    supercorp-ai · Tools & apps

  23. 0396

    Stanley Code

    Bounded Jev workflows for coding agents (formerly jev-code).

    devagrawal09 · Tools & apps

  24. 0395

    slop-grader

    Rule-based text grader that uses Jev scores and line-by-line flags to audit documents against custom rulesets and guide an AI agent to auto-fix violations.

    lukstei · Tools & apps

  25. 0394

    ruby_decision_model

    Ruby client with standard-library transport for TypeSafe and OpenRouter decision endpoints.

    obie · Tools & apps

  26. 0393

    Rig

    Rust `rig-typesafeai` crate with typed Choice, Score, and Noul queries, response validation, examples, and fixtures.

    0xPlaygrounds · Tools & apps

  27. 0392

    Pydantic AI

    TypeSafe model provider that derives Jev questions from Pydantic output types and supports typed routing and fallback workflows.

    pydantic · Tools & apps

  28. 0391

    Prism

    Liquidity-provision agent for Meteora DLMM.

    irfndi · Tools & apps

  29. 0390

    pi-warden

    Pi extension that judges rule compliance, risky actions, stuck loops, and completion claims; enforcement depends on the hook and policy.

    DevMortimer · Tools & apps

  30. 0389

    pi-jev-context

    Opt-in Pi extension that filters older messages from model requests while preserving the original session history.

    kevinpita · Tools & apps

  31. 0388

    pi-jev-compact

    Selective, verbatim context compaction for Pi using Jev model.

    ilkerulusoy · Tools & apps

  32. 0387

    pi-fast-jev-compaction

    Pi extension that prunes stale tool history and leaves summary compaction to Pi when pruning is insufficient.

    joelhooks · Tools & apps

  33. 0386

    Pi Jev Guard

    Pi coding-agent plugin with rules configured by timing, plus risk checks, output redaction, and reminders on repeated failures.

    zszz3 · Tools & apps

  34. 0385

    perch

    Semantic code linter that evaluates code units against configurable Jev questions.

    lakeday-org · Tools & apps

  35. 0384

    parallelConstraintDecoding

    Java and llama.cpp experiments in parallel constrained decoding.

    stephanj · Tools & apps

  36. 0383

    oxlint-plugin-jev

    Oxlint rules written as plain-English questions about a function, call, JSX element or file, reported when the yes-probability clears your cutoff.

    wobsoriano · Tools & apps

  37. 0382

    OpenThai-SystemOne

    Thai and English decision model with a slot-softmax head whose request and response shape mirrors the official API, so existing SDK code can point at it.

    iapp-technology · Tools & apps

  38. 0381

    opencode-jev-orchestrator

    Keeps an OpenCode parent model fixed and uses Jev difficulty judgments to delegate harder turns to temporary subagents.

    aaronshaf · Tools & apps

  39. 0380

    Open Jev (intikhab49)

    A 150M encoder trained to answer typed questions in one pass, with the training notebook written to run on a free GPU.

    intikhab49 · Tools & apps

  40. 0379

    minojev

    Head-training reproduction: a frozen Qwen3-1.7B backbone plus a ~0.8M-parameter decision head returns calibrated Choice/Boolean/Score distributions in one forward pass with zero…

    zeredy879 · Tools & apps