Projects tagged with “llm”
Browse Jev GitHub projects tagged with llm. Filter, sort and explore their source repositories.
- 1977jev-benchMeasure accuracy and calibration of Jev (TypeSafe AI's decision model) on public datasets: 12 business-like tasks, 7 experiments, one Python file.
Running-Dolphins/jev-bench · Python
00benchmarkcalibrationllmpython - 2000jev-calibrationIs TypeSafe AI's Jev calibrated? Reliability diagram, ECE and saturation split on 240 hand-labelled agent tool calls.
themsquared/jev-calibration · Python
00agentevalsagentgatewayai-agentsbenchmarkcalibrationllmpython - Jev + Claude Code, tested: a support-triage app and a Claude Code safety hook where TypeSafe's Jev makes the fast typed decisions and code owns the rest. Runs offline; --live for Jev.
gsaini/jev-claude-code-case-study · Python
00agentic-aiai-agentscase-studyclaude-codeclaude-code-hooksllmpython - 2027jev-cliFast yes/no, choice and score decisions from your shell, powered by TypeSafe AI's Jev model. Unofficial CLI.
2b3pro/jev-cli · TypeScript
00bunclassificationclillmshelltypescript - 2039jev-compilerCompile decision policies into inspectable, measurable TypeSafe Jev programs.
triggeredcode/jev-compiler · Python
00decision-systemsllmollamaopenrouterpythonworkflow-compiler - 2054jev-cookbook把 Jev(一个小而快的判定器)接进你的 AI 助手:一个多月的实战手册——接入 / 判定点 / 影子期评测 / 踩坑集
zhaoyanan-pixe/jev-cookbook · Python
00agent-skillsai-agentscookbookjudgmentllmpython - Corrective RAG where every decision gate is a typed System One model call instead of an LLM judge. 7x fewer LLM calls, 4x lower p50 latency.
sudeshkar/jev-corrective-rag · Python
00ai-agentsgroqllmpythonragretrieval-augmented-generation - 2056jev-craft让 Agent 长出「操作杆」:用 System One 模型(Jev)承担高频判断、多模态模型当眼睛。给思路 + 可跑的参考实现(75 条离线断言,零依赖零 key)
1816586742-stack/jev-craft · JavaScript
00ai-agentsdecision-makingdeepseekdshllmminecraft - 2057jev-crash-courseAn 11-level crash course on Jev, TypeSafe AI's System One decision model — runnable examples against the real API, plus a capstone project with unit tests and evals. Works with any LLM provider via LiteLLM.
nadyth/jev-crash-course · Python
00ai-agentscrash-courseevaluationlitellmllmpython - 把决策模型(typesafe/jev-1.13,经 OpenRouter 的 decisions 端点调用)封装成业务决策工具:注册表驱动,带置信度门控与硬约束。非官方项目。
Wany-i/jev-decision-layer · Python
00agent-toolsdecision-makingguardrailsllmmcppython - 2123jev-eval-harnessLLM-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
00anthropicciclaudeeval-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
00agent-skillsclaudeclaude-codellmtoken-efficiencypython - 2173jev-goal-reflexSteer a 3D box with plain-language goals: an LLM (System 2) plans each instruction, TypeSafe Jev (System 1) makes every move, turn and jump decision in real time. Three.js + TypeScript.
blakeandrewwood/jev-goal-reflex · TypeScript
00ai-agentsgame-aillmreal-timesystem-twothreejs - 2181jev-hankoMeasuring TypeSafe AI's Jev on 41-clause contract review (CUAD, 20,500 decisions) against fast, cheap LLMs — latency, cost and F1
matu79go/jev-hanko · Python
00benchmarkcontract-reviewcuadlatencylegal-aillmopenrouter - Compile fixed decision tasks into reusable heuristic programs.
Ki-Seki/jev-heuristic-adapter · Python
00llmpython - 2213jev-javaJava 21 client for TypeSafe's Jev evaluator: typed questions, typed answers, no decisions made for you
tcheeric/jev-java · Java
00jev-apillmjava - 2220jev-judgeCalibrated judgments for social posts, powered by Jev: relevance, quality, spam, kinds of post, how human a draft reads, and what someone keeps.
simojam93/jev-judge · TypeScript
00ai-writingllmrankingsocial-mediaspam-detection - 2232jev-labHands-on experiments with TypeSafe's Jev (System One model): primitives, routing, ranking, with captured outputs and lab notes
HurayrahB/jev-lab · Python
00hackathonllmpython - 2288jev-no-enemReproducible benchmark evaluating TypeSafe AI's Jev (System One paradigm) on Brazil's ENEM 2025 standardized exam. Evaluates typed decision-making, domain-specific accuracy, and RLCD uncertainty calibration against open LLM baselines with an interactive GitHub Pages dashboard.
patryckalves/jev-no-enem · Python
00benchmarkbrasilenemllmrlcdpython - 2304jev-pacmanJev (TypeSafe System One) plays Pac-Man in real time: structured state in, one legal direction out. No screenshots, no fine-tuning.
tetsuya-dev-jp/jev-pacman · TypeScript
00ai-agentsgame-aillmnextjspacmantypescript - 2323jev-playgroundJev 本地测试台(非官方) / Unofficial local playground for TypeSafe AI's Jev System One decision model
xingqiux/jev-playground · HTML
00decision-modelllmplaygroundhtml - Local browser playground for TypeSafe's Jev decision model via OpenRouter. Python stdlib only.
octanevz/jev-playground-openrouter · JavaScript
00llmopenrouterplaygroundjavascript - 2365jev-req-gateA quality gate for AI-generated requirements, powered by Jev (TypeSafe System One). Routes each requirement to PASS / REVIEW / BLOCK with calibrated probabilities. Real benchmark vs LLM: 0 false blocks, 9x cheaper.
thomaszta/jev-req-gate · Python
00developer-toolsllmquality-gaterequirements-engineering - 2366jev-rerankJev-powered relevance filtering and reranking for RAG. Score, sort, and filter retrieved passages with one batched call. Drop-in reranker at a fraction of hosted-rerank cost.
CMaintz/jev-rerank · Python
00embeddingsinformation-retrievallangchainllamaindexllmnlp - Probabilistic soft-constraint evaluation for volunteer scheduling using TypeSafe Jev, with deterministic application policy.
WINEEL/jev-scheduling-evaluator · Python
00decision-modelfastapillmnextjspythonscheduling - 2386jev-screenTurn an investment idea into an evidence-backed stock list: Jev reads ~20k global companies and checks official annual reports. 主题选股 / 产业链 / 年报证据 — runs locally via your AI agent.
YuanTong-Wu/jev-screen · Python
00a-sharesai-agentsannual-reportsclaude-codeinvestment-researchllmstock-screener - Streamlit app that triages support tickets with Jev (TypeSafe AI), with a human review queue and MySQL backed labels.
kokorani/jev-support-ticket-triage · Python
00human-in-the-loopllmmysqlpythonsqlalchemy - Autonomous dinosaur ecosystem where code runs the physics and TypeSafe's Jev decides each creature's intent from prose laws. Pixel-art web UI with a live Jev monitor (JSON in/out per tick), interchangeable brains (hybrid / full Jev / offline). Experimental Jev integration.
ChristianTracy/jev-terrarium-dinosaurs · Python
00ai-agentsautonomous-agentsfastapillmpixel-artpythonsimulation - Fast 'System One' reflex for reasoning LLMs: typed probabilistic second opinions from Jev via OpenCode Zen, with PII-minimizing state redaction.
OmarAlaaeldein/jev-verifier-skill
00agent-skillsai-agentsllmopencodeprivacy - 2495jev-vs-layaJev(TypeSafe AI System One Model) 스터디 — 타입화된 결정·RLCD·confidence-gated routing을 한국어 노트와 TypeScript 목업으로 정리
wjdjdakf17/jev-vs-laya · TypeScript
00decision-modeljevlikellmstudy-notes - Does a System One model actually beat keyword matching? A reproducible benchmark on catching disguised duplicate thesis titles. 24 cases, real production baseline, raw data and charts included.
devnolife/jev-vs-tfidf-benchmark · TypeScript
00benchmarkindonesiainformation-retrievalllmplagiarism-detectionstructured-outputtf-idf - 2504jev-whereJEV WHERE? A seek-and-find for the decisions hiding in your code. Claude Code plugin that finds where Jev fits in your app.
cesarroger/jev-where · Python
00claude-codeclaude-code-pluginclaude-skillscode-analysiscode-auditllmstatic-analysis - 2551jevidenceLet Jev judge. Let your code decide. Python issue-routing sandbox with labeled replay, an offline demo, and Kev support.
peakevergreen/jevidence · Python
00classifierguardrailshuman-in-the-loopissue-triagellmpythonreplay - 2578jevqFour linters in this ecosystem are powered by Jev. None lints the Jev questions themselves. Nine rules from TypeSafe's own documented failure modes, no API key, no labelled data, 0.03s.
yodablocks/jevq · Python
00clilinterllmprompt-engineeringpythonstatic-analysis - 2603jevxjevx is a compiler from vim-regex-flavoured line inputs to JSON responses for token efficient tool usage
rotkonetworks/jevx · Zig
00agentic-aiexecutellmregexshellvimvimscript - 2619junaA lean Pi coding agent profile that keeps context small, with TypeSafe Jev pruning tool output
safzanpirani/juna · TypeScript
00ai-agentscoding-agentscontext-engineeringexallmpi-coding-agentprompt-caching - 2664mars-gateA semantic-decision benchmark comparing Jev with general-purpose LLMs in a fictional Mars entry checkpoint.
komzweb/mars-gate · TypeScript
00benchmarkllmreacttypescript - Pick the right AI model and effort before an agent starts: Jev plugins for Claude Code and Codex, a local chat app for both, and an MCP completion gate.
haskallalk-eng/mindrails-supervisor · JavaScript
00agent-evaluationai-agentsclaude-codecodexllmmcpmcp-server - TypeSafe (Jev) AI client for Magento 2 — shared connection, response cache and token budget for DMLab AI modules
dmlab-work/module-typesafe-core · PHP
00adobe-commerceai-clientclassificationllmmagentomagento2
201–250 of 261