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 “llm”

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

  • 飞书 Jev 回复助手:点一条消息,看懂对方、给出可直接复制的回复。发不发由你。

    Hatuw/jev-chat-feishu · TypeScript

    10
    chat-assistantdeepseekfeishularkllmreply-assistant
  • An 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.

    nadeemcite/jev-crash-course · Python

    10
    ai-agentscrash-courseevaluationlitellmllmpython
  • Vets an LLM agent's tool calls through TypeSafe AI's Jev before they run — allow, block, or hold, failing safe on uncertainty.

    CMaintz/jev-guard · TypeScript

    11
    ai-agentsai-safetyguardrailsllmtypescript
  • Jev Hub: ready-to-run Jev examples and cost data (independent, not affiliated with TypeSafe AI)

    shiiivvaam/jev-hub · JavaScript

    10
    awesome-listdecision-modelllmjavascript
  • Experiments with TypeSafe's Jev decision model: a feed sieve that judges a week of posts from 500+ public feeds against a reader's interests, and a bookmark-categorisation eval.

    gregoryjayuk/jev-lab · Python

    10
    ai-evaluationinformation-filteringllmpythonrss
  • 最简 Jev 调用演示器:单页分类器,把请求 JSON、概率分布、confidence、耗时与 token 都摊开给你看

    Zorien-ai/jev-lab · HTML

    10
    classifierllmpythonhtml
  • Hands-on research lab for TypeSafe's Jev (System One model): reproducible benchmarks of Noul/Choice/Score primitives, confidence gating, fan-out latency, agent control — plus a living audit of the Jev ecosystem.

    llt22/jev-lab · Python

    10
    ai-agentsbenchmarkconfidence-calibrationevaluationllmllm-evaluationllm-observability
  • Jev-compatible /v1/systemone server reading typed decisions from LLM logits, benchmarked against TypeSafe's Jev on the same items via JevBench

    dashbi1/jev-sim · Python

    10
    benchmarkcalibrationclassificationllmlogprobspython
  • AI columns for CSV/JSONL files with TypeSafe's Jev — typed answers, confidence, review queue, resume and cost preview. Local-first, BYO key.

    dtduc-git/jev-table · Python

    10
    classificationclicsvdata-labelingllmpython
  • Table tennis vs. TypeSafe's Jev (System One). Every paddle move on the right is a live model decision — no local prediction, just a lookup table and a servo.

    LiuHao-1443/jev-table-tennis · Python

    10
    ai-agentscanvasgamehuman-vs-aijavascriptllmprompt-engineering
  • A lightweight, auditable Jev testbench built through Agentic Engineering, with frozen evidence, a preregistered null result, and a bilingual technical blog. 基于 Agentic Engineering 的轻量、可审计 Jev 实验台,包含冻结证据、预注册负结果、双语技术博客与认知负债反思。

    Charlie-Wang-03/jev-testbench · Python

    10
    agentic-engineeringai-agentsllmmodel-evaluationpreregistrationprobabilistic-aipython
  • 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
  • Jev (TypeSafe System One) plays Zork I: one Choice per move over Jericho's valid actions, with its confidence on display. French dashboard.

    Resadan-dev/jev-zork · Python

    10
    jerichollmpythontext-adventurezork
  • jevkit for JavaScript/TypeScript: static linter and shared record format for building on TypeSafe's Jev (System One) model. Unofficial.

    pjdurden/jevkit-js · TypeScript

    10
    linterllmtypescript
  • A policy engine for LLM decisions: declare routes, gates and actions once in TypeScript or Python, and every decision comes validated, explainable, replayable and audited.

    TimMikeladze/JevLang · JavaScript

    10
    ai-agentsauditdecision-engineguardrailsjevlangllm
  • 1474loom
    Generate a landing page from one sentence: an LLM writes the copy, Jev makes the judgement calls, code owns the rules.

    yldm-tech/loom · TypeScript

    10
    design-systemgenerative-uijson-renderlanding-pagellmnextjs
  • Cache the decision, compute the policy. Record typed decisions from Jev-class System One models under a key built from state, question, and model, then change thresholds, review bands, routing, and budgets without re-running anything.

    YYTbit/metajev · Python

    11
    calibrationdecision-modelllmpolicypythontyped-decisions
  • Model Picker: JEV-powered Codex model and effort recommendations as task scope grows. Manual switching, private local state, MIT licensed.

    Tatendaz/model-picker · Python

    10
    ai-codingcodexcodex-plugindeveloper-toolshooksllmmodel-routing
  • Find the LLM calls you should move to JEV — scan logs & code for decision-shaped calls, price the migration, calibrate decision models, generate the migration PR. Zero deps, fully local.

    yzbcs/Should-I-Jev · Python

    10
    cost-optimizationdeveloper-toolsllmpython
  • 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
  • Alert triage as a UNIX filter: JSONL security alerts in, typed decisions out. Runs on TypeSafe Jev or a local model; policy routing stays in code.

    m0rphtail/triagedy · Rust

    11
    alert-triageclillmrustsecuritysoc
  • Ruby client for Jev, TypeSafe's System One model: typed questions, probabilistic answers. Zero runtime dependencies.

    dtheofr/typesafe-jev-ruby · Ruby

    10
    gemllmrubyrubygemstypesafe-api
  • Typed AI decisions for .NET: ask Jev (TypeSafe AI System One) yes/no, choice and score questions and get a C# enum with calibrated probabilities back.

    RavenValentin/TypeSafe.Jev · C#

    10
    aotclassificationc#decision-enginedotnetllm
  • Typed Go client for the TypeSafe System One API (Jev): structured questions and answers your code can act on. Community SDK, MIT.

    mheers/typesafeai-systemone-jev-go · Go

    11
    api-clientgollmmachine-learningsdkstructured-output
  • Modular typed decisions (Jev-type) endpoint for vLLM: /v1/decisions with /v1/systemone compatibility, pluggable readout backends

    Timiku/v1-decisions-vllm · Python

    10
    classificationinferenceinference-apillmtyped-decisionsvllmpython
  • Fast computer-use agent for macOS: Gemini plans once, Jev acts at every step via the Accessibility API

    omerfeyzioglu/agentp-macos · Python

    00
    accessibilityai-agentscomputer-usellmmacosvoice-assistantpython
  • 1623ak-jev
    Node.js bindings for TypeSafe's Jev — the System One model. Typed decisions, probabilities and confidence, with no text generation and no parsing.

    ak--47/ak-jev · JavaScript

    00
    classificationguardrailsllmnodejsreranking
  • Reproducing the Jev decision interface

    our0boros/AnyLM2Jev · Python

    00
    calibrationllmpython
  • 1644assay
    Fast, local, typed decisions with calibrated confidence. An open take on the System One / Jev idea.

    patkusch/assay · Python

    00
    ai-agentscalibrationllmlocal-llmpython
  • A source-backed catalog of real TypeSafe Jev projects, integrations, experiments, and workflows.

    FuturExplorator/awesome-jev-cases · Python

    00
    agent-toolsai-agentsawesomeawesome-listbrowser-automationcase-studiesllm
  • A curated list of decision models similar to, alternatives to, or reimplementations of Jev (TypeSafe AI's System One model for typed decisions).

    notsointresting/awesome-jev-family · Python

    02
    awesomeawesome-listlayalaya-mlxllmopenjevpython
  • Use Jev instead of an LLM for RAG decisions: relevance grading, query routing, hallucination checks and LLM-as-a-judge evals. Faster, cheaper, measured first.

    davidzna/better-cheaper-llm · Python

    00
    cost-optimizationgroundednessguardrailshallucination-detectionllmllm-as-a-judgellm-evaluation
  • 1678bivio
    Decisioni tipizzate da un modello linguistico, sul tuo computer, senza generare un token. La versione libera dell'idea di Jev.

    TheRealF/bivio · Python

    00
    classificationitalianollama-cppllmlocal-firstlogitstyped-output
  • Adversarial browser testing: personas explore your web app while Jev judges every page state

    DowLucas/browser-jev · TypeScript

    00
    ai-testingbrowser-testinge2e-testingexploratory-testingllmplaywrightqa
  • 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
  • MCP server in Go for LLM-powered (Jev) classification of text, local files, and line ranges using custom criteria.

    n-r-w/classifier-mcp · Go

    00
    ai-toolsfile-classificationgollmmcpmcp-servermodel-context-protocol
  • Reduza tokens de entrada no Claude Code com compactação de contexto por relevância (LiteLLM + TypeSafe Jev). Tutorial bilíngue PT-BR / EN.

    DihRJ/claude-code-jev-compaction · Shell

    00
    claude-codecontext-managementlitellmllmshell
  • Find where an API router confuses look-alike operations, rewrite the wording, and rerun. Runs offline in mock mode; live mode uses TypeSafe's Jev.

    Chaddacus/crosstalk-lab · TypeScript

    00
    data-visualizationevaluationllmopenapitool-routingtypescript
  • 1747Davout
    Jev-style typed decisions (yes/no, choice, score with calibrated probabilities) on HRM-Text-1B, with benchmarks against OpenJev and teacher distillation

    ruhalis/Davout · Python

    00
    calibrationhrmknowledge-distillationllmtext-classificationtyped-decisionspython

151–200 of 261