A free GitHub project directory for the TypeSafe Jev / System One model.Explore official SDKs, agent tools, open-source alternatives and Jev news.

Data updated

All tags

Projects tagged with “claude”

Browse Jev GitHub projects tagged with claude. Filter, sort and explore their source repositories.

  • an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch

    kyegomez/open-jev · Python

    15127
    anthropicattentionchatgptclaudegpttransformers
  • Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.

    UditAkhourii/quicksilver · JavaScript

    14212
    ai-agentsclaudeclaude-codedeveloper-toolsllmskillstokens
  • MCP server and CLI that crawls websites for AI agents: finds the answer page 2x more often than Crawl4AI, 10x cheaper per answer than letting Claude crawl.

    RayenMlayeh/jevcrawl · Python

    898
    ai-agentsclaudecrawlerllmmcpmcp-serverpython
  • 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

    514
    acpai-agentsclaudecomputer-usegrokllmopencode
  • Claude Code plugin that auto-picks the right model for each turn — micro, low, medium, or high tier — using Jev routing.

    alexei-led/claude-router · JavaScript

    467
    anthropicclaudeclaude-codellmmodel-routingplugin
  • Claude Opus 5.5 with the effort level re-decided every step by the TypeSafe Jev reflex — without breaking the prompt cache. CLI + Claude Code plugin.

    WXK-AI/jev-opus · TypeScript

    182
    ai-agentsclaudeclaude-codeclaude-code-plugineffortopusprompt-caching
  • 📏 Claude Code plugin that makes Claude follow your AGENTS.md: every reply and edit checked by TypeSafe Jev ✅

    erkamyaman/jev-enforce · TypeScript

    132
    claudeclaude-codeclaude-code-pluginclaude-mdcode-qualitydeveloper-tools
  • Check whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides.

    MarissaFamularo/citation-verifier · JavaScript

    122
    javascriptcitation-verificationclaudepeer-review
  • A Claude Code plugin that keeps your AI agents honest. Claude plans tasks as phases with checks, and when it tries to stop, Jevflow runs them and asks Jev if the work is really done. Many agents, one plan, with a live viewer to watch it all.

    Parth1811/JevFlow · Python

    120
    claudeclaude-codeclaude-code-hooksclaude-code-marketplaceclaude-code-pluginclaude-code-pluginsclaude-code-plugins-marketplace
  • Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

    ShivamPansuriya/jev-skill-gate · JavaScript

    81
    agent-skillsai-agentsai-toolinganthropicclaudeclaude-codeclaude-code-hooks
  • Talk to your Mac and it does it — in any app, while you're still talking. Open-source voice agent that gets faster the more you use it.

    danielyedaniel/jevme · Python

    61
    accessibilityai-agentsanthropicautomationclaudecomputer-usellm
  • Learn decision models by building with them. TypeSafe Jev and Microsoft Decision-1 route support tickets in under a second for about $0.02 per 1,000 calls; Claude handles the hard cases. Interactive site, benchmark, calibration tests and docs.

    shashikantdev3/decision-models-lab · TypeScript

    50
    ai-agentsanthropicbenchmarkcalibrationclaudedecision-modelhuman-in-the-loop
  • Open-source Jev skills for Claude Code, Codex, Cursor, and Grok. TypeSafe System One: choice, noul, score. Proceed, ask, or stop.

    aitofy-dev/jev-awesome-skills · TypeScript

    41
    agent-skillsawesome-listclaudeclaude-codecodexcursorgrok
  • Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.

    MongLong0214/jev-gate · TypeScript

    40
    agentic-aiai-agentsai-coding-assistantai-engineeringanthropicclaudeclaude-code
  • Per-turn router for agent harnesses: one 350ms Jev call picks the model tier, effort, tools and skill, behind a hard deadline with a regex fallback. Claude Agent SDK adapter included.

    JoacoMarc/jev-harness-router · TypeScript

    41
    ai-agentsclaudeclaude-agent-sdkcost-optimizationharnessllm-routing
  • High-speed dual-process browser agent combining sub-150ms Jev reflex decisions with Stagehand stealth automation and Gemini/Claude System 2 fallback.

    adnanahmaddev/system-one-browser-agent · TypeScript

    40
    browser-automationbrowser-useclaudegeminillm-agentsplaywrightstagehand
  • 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

    31
    agent-securityai-agentsai-safetyanthropicbypass-permissionsclaudeclaude-code
  • A retrieval engine that reasons over document structure — not embeddings. No chunking, no top-K, no vector DB.

    hallelx2/vectorless-engine · Go

    31
    ai-agentsai-infrastructureanthropicclaudedocument-aidocument-search
  • MCP server and skill that let an agent drive an Android phone naturally over adb

    FZ2000/android-jev · Python

    20
    adbai-agentsandroidandroid-automationautomationclaude
  • Decisões tipadas para o código (TypeSafe Jev) e texto livre para pessoas (LLM). Custo zero por padrão.

    thiago-lage/jev-claud · Python

    20
    claudellmpython
  • 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
  • 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
  • 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
  • Claude Code plugin and Python CLI: hand a judgment repeated over many items to TypeSafe's Jev, with redaction, rate limiting, a pilot and a flat-question check.

    bitranox/btx-skill-jev-judge · Python

    10
    agent-skillsai-agentsanthropicbatch-processingclassificationclaudeclaude-code
  • /compact-jev: Jev-guided verbatim compaction for Claude Code through Vercel AI Gateway, separate from /compact.

    edoproch/compact-jev · TypeScript

    11
    claudeclaude-codeclaude-code-plugincontextcontext-compactioncontext-engineeringcontext-window
  • F´ flight software → CCSDS/Yamcs → Open MCT, with jev (System One) and Claude Sonnet 5 (System Two) driving Doom over that real mission stack.

    doom-satellite/DoomSat · Python

    11
    ccsdsclaudefprimeopenmctyamcspython
  • Benchmark TypeSafe's Jev (System One model) vs Claude on structured decisions: accuracy, latency, calibration, cost

    stern9/jev-bench · Python

    10
    anthropicbenchmarkclaudeevaluationllmpython
  • A zero-dependency MCP server for TypeSafe's Jev — calibrated, typed judgments for Claude Code, with a local answer cache and cost tracking.

    lhviet/jev-bridge · JavaScript

    10
    claudeclaude-codellmmcpmcp-servermodel-context-protocol
  • Messy documents in, tagged library out. Jev scores every file against your taxonomy, Haiku reads the scans, and every tag is written into the file and verified.

    ClehmanGit/jev-cleaning-and-tagging · Python

    10
    claudedocument-classificationmetadataocrpdfragtaxonomy
  • A growing kit of Jev-powered tools for Claude, ChatGPT, your browser and your terminal, starting with Laugh Track.

    leighefford/jev-kit · JavaScript

    10
    claudelaugh-trackmcppublic-speakingjavascript
  • Jev Lab — Arabic demo of TypeSafe Jev: decisions in <0.5s, plus a browser agent where Jev clicks and Claude thinks. From youtube.com/@malkhatib

    makhatib/jev-lab · JavaScript

    11
    ai-agentsarabicbrowser-agentclaudedockerjavascript
  • The doorman for Claude’s context window. JEV-powered model routing and recoverable context filtering for Claude Code.

    cvsgireesh/jev-usher · TypeScript

    10
    ai-agentsclaudeclaude-codeclaude-code-plugincontext-engineeringcontext-windowllm
  • Claude Code + Codex CLI plugin that verifies the agent follows project rules through a System One (Jev) model

    Jhonnyr97/JevGuard · TypeScript

    10
    agent-securityagent-skillsai-agentsclaudeclaude-codecodex
  • Frontier prices only for frontier work: each task goes to the cheapest model that does it well, a request is split only when that pays, and every result is checked. Decisions by Jev.

    cintocasals/taskpenny · Python

    10
    ai-agentsbenchmarkclaudecost-optimizationgeminillmllm-routing
  • Typed decision tools for AI agents, powered by TypeSafe Jev

    Renwang-Huang/arbitype · Python

    01
    ai-agentsclassificationclaudecursordecision-makingguardrailsllm-evaluation
  • 1705choola
    Python framework for building automations with AI coding agents — single-file nodes, JSON payloads, built-in LLM cost guardrails.

    igrosny/choola · Python

    00
    ai-agentsautomationclaudeclaude-codedagframeworkllm
  • Use Jev (TypeSafe AI) with Claude Code and Codex: hooks that warn when you or your agent drift off task

    benpchandler/drift-guard · Python

    00
    ai-agentsclaudeclaude-codecodexcoding-agentshooks
  • LLM-as-a-judge evaluation harness: a confidence-gated cascade (fast typed judge → Claude) that scores LLM outputs and gates CI on a regression diff. TypeScript, real recorded transcripts, real benchmark numbers.

    laszloblum/jev-eval-harness · TypeScript

    00
    anthropicciclaudeeval-harnessevaluationllmllm-as-a-judge
  • Agent Skill that offloads bulk yes/no, pick-one-option and rating judgments to TypeSafe's Jev so Claude spends fewer tokens during investigations.

    rukshan99/jev-fast-judgements · Python

    00
    agent-skillsclaudeclaude-codellmtoken-efficiencypython

1–42 of 42