shipwithjev

Tools & apps

247 builds · page 3 of 7

  1. 0384

    parallelConstraintDecoding

    Java and llama.cpp experiments in parallel constrained decoding.

    stephanj · Tools & apps

  2. 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

  3. 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

  4. 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

  5. 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

  6. 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

  7. 0378

    lorenzini

    Claude Code skills that wait for CodeRabbit, Copilot or Codex to finish reviewing a pull request, then judge whether the verdict actually permits a merge.

    Nanako0129 · Tools & apps

  8. 0377

    LiteLLM

    Jev-backed complexity routing and an optional relevance guardrail for compacting tool results before they return to an agent.

    BerriAI · Tools & apps

  9. 0376

    Laya Vision

    Research fork of Laya that replaces its text encoder with SmolVLM-256M so typed `choice` and `noul` decisions are read from an image plus optional text in one forward pass with…

    r33drichards · Tools & apps

  10. 0375

    LangChain.js

    JavaScript/TypeScript classifier Runnable and middleware for bounded routing and tool-call checks.

    langchain-ai · Tools & apps

  11. 0374

    LangChain

    Python `TypeSafeClassifier` Runnable with batched typed questions plus model-routing and risky-tool middleware.

    langchain-ai · Tools & apps

  12. 0373

    Jot

    A general-purpose agent loop where Jev picks the next move and Jot runs it.

    runta-dev · Tools & apps

  13. 0372

    jgrep (kyu1204)

    Semantic grep for code, git diffs and CSV rows: one Noul per 5-60 line chunk, 16 chunks per Jev request, grep-style file:line output and exit codes for CI lint rules written in…

    kyu1204 · Tools & apps

  14. 0371

    jevvy

    Plugins for coding agents, starting with one that auto-approves shell permission requests it judges harmless and passes everything uncertain to the normal flow.

    PanAchy · Tools & apps

  15. 0370

    Jevthoven

    Symbolic-music studio where Jev chooses plans, instruments, and bar patterns, and code renders editable music and MIDI.

    cocktailpeanut · Tools & apps

  16. 0369

    jevscan-evm

    Produces a heat map of likely bugs in EVM code.

    devtooligan · Tools & apps

  17. 0368

    JevRouter

    Routes agent requests across models, subagents, skills, MCP tools, CLIs, and plugins with Jev Choice decisions; the host filters by availability, permissions, risk, and…

    BillionsBobby · Tools & apps

  18. 0367

    jevr

    Native R client for typed questions and provider-independent answers through TypeSafe or OpenRouter.

    simxnherrera · Tools & apps

  19. 0366

    JevLint

    Checks code against conventions written in plain English, in a write-check-fix loop with your coding agent.

    huntedman · Tools & apps

  20. 0365

    Jevify

    Agent skill for finding where Jev fits in an existing codebase, designing the typed questions, and measuring whether it helped.

    altryne · Tools & apps

  21. 0364

    Jevbridge

    ACP/MCP adapter for using Jev alongside coding and chat models.

    gamesonrblx · Tools & apps

  22. 0363

    JevBench

    Benchmark for typed decision models across several suites, with confidence cascades and committees reported separately.

    fstandhartinger · Tools & apps

  23. 0362

    jev-trade

    Hyperliquid trading desk where Jev answers Choice questions for long/short, open/close/hold, and leverage; application code quotes or sends no order.

    aowang-ai · Tools & apps

  24. 0361

    jev-scout

    MCP server that scores an agent's every search query, result, and fetched page for relevance and credibility, with session budgets, SSRF-guarded fetching, and a live decision…

    kierandotai · Tools & apps

  25. 0360

    jev-review MCP plugin

    Local-first continuous software-quality review for coding agents.

    NiazMorshed2007 · Tools & apps

  26. 0359

    jev-repl

    Terminal REPL for shaping System One requests before writing code.

    aoprisan · Tools & apps

  27. 0358

    jev-pref

    Linter that has Jev check code changes against project preferences from `jev-pref.json` and feeds findings back to coding agents.

    doeixd · Tools & apps

  28. 0357

    jev-logtriage

    Jev scores collapsed log batches for noise, severity, and whether an operator should act.

    jyatesdotdev · Tools & apps

  29. 0356

    jev-lint (mizchi)

    Checks whether a function does what its name says, whether a comment is still true, and whether a test verifies what it claims, with a cutoff per rule.

    mizchi · Tools & apps

  30. 0355

    jev-guard

    Cross-agent tool-call risk scoring with allow, ask, and deny outcomes.

    leepokai · Tools & apps

  31. 0354

    jev-gateway

    Local gateway for Codex and Claude Code that asks Jev which tool to call next and passes everything else to your usual model.

    vinilana · Tools & apps

  32. 0353

    jev-gates

    Seven calibrated gates for Claude Code (rules, scope, intent, done, claims, proof, and commit honesty) that escalate but never approve.

    rashedInt32 · Tools & apps

  33. 0352

    jev-eval-mcp

    Eval-first MCP server that focuses on knowing whether Jev's answers can be trusted for your task.

    BYK · Tools & apps

  34. 0351

    jev-eval-agent

    Compares LLM tool selection with Jev routing in a personal-assistant harness containing 100 mocked tools.

    vinilana · Tools & apps

  35. 0350

    jev-engineering

    Decision layer for coding agents: deterministic hard rules, then a Jev call, exposed as a Claude Code PreToolUse hook, an MCP server, a loopback service and a shared team policy.

    eugeniughelbur · Tools & apps

  36. 0349

    jev-dsl

    Early-alpha Haskell DSL that encodes typed question packets and decodes answers; HTTP transport is left to the caller.

    inanna-malick · Tools & apps

  37. 0348

    jev-decision-benchmarks

    Independent evaluation of Jev on MetaTool, When2Call, and BFCL V4 agent decision tasks, focusing on tool selection, abstention, and tool-use decisions.

    baibizhe · Tools & apps

  38. 0347

    jev-commit

    Pre-commit hook where one Jev call judges whether the commit message matches the staged diff, flags debug leftovers and unmentioned work, and blocks only when it detects a…

    valentynkit · Tools & apps

  39. 0346

    jev-codex-router

    Per-turn Codex model, reasoning, and speed-mode routing.

    0xNatoshi · Tools & apps

  40. 0345

    jev-belay

    Claude Code Stop hook that checks the transcript for evidence before trusting a "done" claim, spending one four-question Jev call only when files changed with no passing check…

    valentynkit · Tools & apps