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

  • LangChain + Jev (TypeSafe) tutorial: a support-ops agent whose small decisions (triage, model routing, tool guarding, evals) are made by Jev. Real run outputs included.

    PromptEngineer48/langchain-jev-tutorial · Python

    21
    ai-agentslangchainlangsmithllm-evaluationpython
  • A native LangGraph conditional edge that replaces slow generative LLMs with TypeSafe AI's deterministic System One model (`Jev`). It enables ultra-fast (sub-500ms), schema-safe routing between specialized agents.

    JTankariya/langgraph-jev-router · Python

    20
    python
  • Run the Laya System One decision model locally behind TypeSafe's Jev wire API, with a demo page

    nvkudva/laya-server · Python

    20
    python
  • Experiment to trick Typesafe’s Jev, aka “the language model that won’t talk” into actually talking.

    suidouble/let-jev-speak · JavaScript

    20
    botchatbotllmjavascript
  • Read pages with Lightpanda, decide where to go with Jev — a self-steering crawler for tiny budgets

    Ejokey/lightjev · Python

    20
    ai-agentscrawlerlightpandapythonweb-scraping
  • A language model plays Unreal Tournament 99 on real Windows 98 hardware by answering small typed questions, several times a second. Any OpenAI-compatible model or Jev.

    loktar00/llm-lan-party · TypeScript

    20
    typescript
  • 1007lmjtfy
    Let Me Jev That For You — ask Jev a yes or no question. Cloudflare Workers + D1 + TypeSafe.

    PostHog/lmjtfy · TypeScript

    20
    typescript
  • Verbatim, reversible, provenance-tracked context compaction for Claude Code (fork of tamaratran/fast-jev-compaction)

    MusicStudioNYC/lossless-compact · TypeScript

    21
    typescript
  • Your Gmail, sorted. Rules you can read, typed AI judgments from TypeSafe's Jev for pennies, receipts and undo for everything.

    Kevin-Liu-01/mailroom · TypeScript

    20
    emailgmailnextjsverceltypescript
  • Typed AI decisions for Codex, Claude and any MCP client, powered by TypeSafe Jev. Classify, score and evaluate with one generic tool.

    MattiooFR/mcp-server-jev · JavaScript

    20
    claudecodexmcpmcp-serverjavascript
  • Decide what an AI system should remember: policy-driven memory gating with typed judgments.

    AfnanHussain10/Memworthy · Python

    20
    agent-memoryai-agentsllmmem0memorypolicypython
  • Experimental local LLM router for OpenAI Codex CLI and Claude Code. Automatically selects models per task using TypeSafe Jev. Free, MIT-licensed, bring your own provider account.

    cybrking/modelrudder · TypeScript

    20
    ai-agentsai-codinganthropicclaudeclaude-codecli
  • Tools for stopping doom scrolling and engaging more productively on the web using TypeSafeAI's Jev Model

    MartianInGreen/NoYouDoNot · JavaScript

    20
    javascript
  • Nushell plugin for TypeSafe Jev structured decisions

    gleb-chipiga/nu_plugin_jev · Rust

    20
    rust
  • nvim-jev-plugin: TypeSafe Jev ecosystem repository.

    balazsorban44/nvim-jev-plugin · Lua

    21
    lua
  • Use TypeSafe's Jev model to auto-tag the current Obsidian note, picking from the tags you already use.

    parthsidpara/obsidian-auto-tagger-jev · TypeScript

    22
    obsidianobsidian-communityobsidian-pluginobsidian-pluginsobsidianmdtypescript
  • Jev, batteries included, for Claude Code, Codex, pi and omp: no permission prompts for safe commands, long output trimmed, the right skill loaded, and destructive commands (rm -rf, force push) or data exfiltration stopped until you say yes.

    novacon/ohmyjev · TypeScript

    21
    agent-securityai-agentsai-safetyanthropicbypass-permissionsclaudeclaude-code
  • TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent

    siddicky/omp-typesafe · TypeScript

    22
    typescript
  • Jev as a message gate to determine if agents should respond

    herval/openclaw-jev-plugin · TypeScript

    20
    typescript
  • TypeSafe Jev-powered intent gate for OpenCode: confirm intent before the agent dives into underspecified requests.

    hoshinodis/opencode-intent-gate · TypeScript

    20
    ai-agentsguardrailsllmopencodeopencode-plugintypescript
  • OpenCode 2 plugin that sends every shell command (local or via FarHand) to TypeSafe's Jev and asks you first when it leaves files outside the project, installs software globally, changes global settings, is harmful or exposes private data

    CogFlux/opencode-jev-guard · TypeScript

    20
    ai-agentscoding-agentsdeveloper-toolsfarhandllm-guardrailsopencodeopencode-plugin
  • opencode-jev-router: TypeSafe Jev ecosystem repository.

    nitoba/opencode-jev-router · TypeScript

    21
    typescript
  • PAVE skill for non-autoregressive decision models (Jev / Laya / TypeSafe): typed Choice, Score and Noul answers with calibrated probabilities

    cnrai/openpave-jev · JavaScript

    21
    javascript
  • Community Paperclip plugin for Jev-powered issue triage and automatic routing.

    zczy318-products/paperclip-plugin-jev · TypeScript

    21
    automationissue-triagepaperclipplugintypescript
  • Automatically select thinking effort for each task useing Jev

    ekil1100/pi-auto · TypeScript

    20
    ai-agentsextensionpitypescript
  • A Jev (TypeSafe System One) permission gate for the Pi coding agent: judges every bash / write / edit call before it runs

    kurihada/pi-jev-permit · TypeScript

    20
    typescript
  • Pi extension that removes the inlined skill list and asks TypeSafe Jev which skill to load

    iamdin/pi-jev-skill-suggestion · TypeScript

    20
    typescript
  • Pi extension: auto-approve routine Bash commands with a System One (Jev) decision model, escalate the rest to a human

    Davidasx/pi-typesafe-approve · TypeScript

    20
    approvalpi-extensiontypescript
  • Chrome extension that scores Idealista rental listings in Spain for scam and contract risk, on the page, powered by Jev

    HusDev/pisocheck · TypeScript

    20
    barcelonachrome-extensioncloudflare-workersidealistamanifest-v3rentalscam-detection
  • 基于 Jev + playwright-cli 的自然语言 Web E2E 测试工具:Jev 负责决策,Playwright 负责执行,代码负责断言与安全边界。Goal-driven web E2E testing with Jev + playwright-cli: bounded AI decisions, real browser execution, and deterministic assertions.

    dingw530/playwright-jev · JavaScript

    20
    playwrightjavascript
  • Structured JEV decisions for Playwright: failure triage, smart retries, healer gating, snapshot pruning, locator healing, semantic assertions, and test impact ordering.

    AdriaanVE/playwright-jev · TypeScript

    20
    typescript
  • A working Demo that acts as classifier to classify linkedin post which inside uses jev by Typesafe.ai

    silky-x0/Postmark · TypeScript

    20
    classificationclassifierllmllm-toolstypefacetypescript
  • Open-source MCP and HTTPS screening for prompts, skills, and tool descriptions using TypeSafe AI Jev, deterministic checks, and configurable reasoning.

    revsmoke/promptrejectormcp · TypeScript

    23
    ai-securityclaudeclaude-codecodexcybersecuritygeminillm-safety
  • 1034qualm
    Typed decisions from a System One model, where uncertainty is something you have to handle.

    qddegtya/qualm · TypeScript

    21
    classificationdecision-makingesmllmtype-safety
  • 1035rev
    Typed decisions from a frozen open model, one forward pass; a local Jev

    54yyyu/rev · Python

    21
    python
  • I tortured Jev into being a RISC-V CPU.

    i2cjak/RISC-jeV · Python

    20
    python
  • Makes S1-model 'measurement' (and the collapse that follows it) a Ruby primitive.

    innocentdiaz/s1_ruby · Ruby

    20
    railsrails8rubyruby-appruby-gemruby-on-rails
  • Report card for your AI coding agent: grades every Claude Code session on disk with Jev, cheaply

    amishah1998/said-done · JavaScript

    21
    javascript
  • semantic-find: TypeSafe Jev ecosystem repository.

    jem-computer/semantic-find · TypeScript

    20
    typescript

3058 件中 1001–1050 件