TypeSafe Jev / System One モデルの無料 GitHub プロジェクト集公式 SDK、エージェントツール、オープンソースの代替実装と Jev の最新ニュースを紹介

データ更新

すべてのタグ

タグ:llm

llm タグの付いた Jev GitHub プロジェクトを検索・並べ替えし、元のリポジトリを確認できます。

  • How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.

    pydantic/pydantic-ai · Python

    20,5652,905
    agent-frameworkgenaiharnessharness-engineeringllmpydanticpython
  • 装在手机上的对话副驾:在 QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框,发不发由你。非侵入,只读屏幕,不 hook 不改包。

    jev-chat/jev-chat-jarvis · Kotlin

    7,6351,250
    accessibility-serviceandroidchat-assistantllmqqkotlin
  • Independent open-source Jev-style decision model that turns open LLMs into typed Choice, Noul, and Score judgments with probabilities.

    nokia-applied-research/AnyJev · Python

    1,202146
    calibrationdecision-modelllmtransformersvllm
  • JevChat-Windows:聊天窗口旁挂的回复辅助。窗口截图 + 本地离线 OCR 读对方消息 → Jev 判断意图 → 3 条候选一键填入,发送永远手动

    jev-chat/jev-chat-windows · Python

    796175
    chat-assistantllmlocal-firstocrprivacypyqtpython
  • A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.

    v-modal/awesome-jev-tools

    74549
    awesomeawesome-listllmroboticsrobotics-algorithmsrobotics-control
  • 🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.

    OmniJev/awesome-jev-gallery · JavaScript

    50232
    awesomeawesome-listcalibrated-probabilitiescalibrationdecision-modelllmllm-evaluation
  • Zero-shot text classification over plain HTTP — no API key, no account. One Cloudflare Worker, a CLI, and an MCP server. https://classifier.dev

    mrmps/classifier-dev · TypeScript

    42533
    apiclassificationclicloudflare-workersllmmcptext-classification
  • Jev-compatible API endpoint based on open models (prefill-only)

    ekzhang/openjev-sglang · Python

    33346
    llmstructured-generationpython
  • Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.

    Shanghua-Gao/RSI-Jev · HTML

    1138
    ai-agentsautonomous-researchdecision-modelllmrecursive-self-improvementtyped-decisions
  • Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.

    openlayer-ai/jevals · Python

    1029
    ai-agentsevaluationguardrailsllmllm-evaluationragas
  • Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.

    Dimweaker/jev-libero · Python

    812
    emobodied-ailiberollmmodel-based-controlmujocorobosuiterobot-manipulation
  • Jev / TypeSafe System One 中文精选列表:官方资料、SDK、爆款应用、Agent 工具、开源复现与独立评测,附中文上手指南,每日自动收录 GitHub 热门项目。

    yzfly/awesome-jev-zh · HTML

    7724
    ai-agentsawesomeawesome-listchinesellmstructured-output
  • Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

    bladedevoff/stuntd · Python

    705
    claude-codedistillationlayallmllm-proxylocal-inferenceopenai-compatible
  • Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks

    ikermoel/open-alternative-jev · Python

    6713
    calibrationclassificationjev-alternativellmlogprobsopen-jevopen-source-jev
  • Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.

    tomerglick57/Jevstiller · Python

    6610
    classificationdistillationknowledge-distillationllmmlopsmodel-cascadepython
  • OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisions and browser-agent steps.

    alanhuangyoo/OpenJev · Python

    620
    browser-agentdecision-modeldistillationjev-alternativellmlocal-llmopenjev
  • An unofficial local visualizer for Jev (TypeSafe): a live view of every call your code makes. Not affiliated with TypeSafe AI.

    andududu/jeview · JavaScript

    6110
    ai-agentsdebuggingdeveloper-toolsllm
  • ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

    tacticocc/Jevbridge · TypeScript

    474
    acpai-agentsclaudecomputer-usegrokllmopencode
  • Go SDK and CLI for TypeSafe Jev: typed decisions (yes/no, choice, score) from a model

    mattn/go-jev · Go

    451
    classificationcligollmsdk
  • ✨✅ The easiest decisions your code will ever make.

    jlowin/vibecheck · Python

    423
    decision-modelllmpython
  • Evidence-backed knowledge graph construction with typed Jev relation decisions

    chenmingtang830/jevgraph · Python

    375
    information-extractionknowledge-graphllmpythonrelation-extraction

199 件中 1–50 件