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.

  • jev: a Jev (TypeSafe System One) toolkit CLI for coding agents — read less, decide with calibrated confidence. Unofficial.

    bragamat/jevkit · Go

    30
    clicoding-agentsgollm
  • Unofficial, dependency-free Go client for the TypeSafe AI System One API and the Jev model. Validated responses, masked credentials, bounded retries.

    KKloudTarus/taurus-jev-sdk-go · Go

    30
    api-clientgogo-sdkllmsdk
  • Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.

    iamvatsalpatel/tiershift · TypeScript

    31
    ai-agentscost-optimizationllmmodel-routingopenai-compatibleproxypython
  • MCP server exposing TypeSafe's Jev model as a typed evaluate tool.

    anasbekheit/typesafe-jev-mcp · Rust

    30
    ai-agentsllmmcpmodel-context-protocolrust
  • Decision circuits: typed questions to a System One model, calibrated probabilities back, gates in code. Zero-dependency Python SDK with LangChain, OpenAI Agents, and Claude Agent SDK integrations.

    Barneyjm/decision-circuits · Python

    21
    ai-agentscalibrationdecision-circuitsguardrailslangchainllmpython
  • High-performance verbatim context compaction for coding agents (Claude, Codex, Antigravity, Gemini, OpenCode)

    satiricalguru/Fast-Jev-Agents · TypeScript

    20
    ai-agentsantigravityclaude-codecontext-compactiongeminillmopenai-codex
  • Decision infrastructure for autonomous software engineering, powered by typed System-1 decision models (Jev). No heuristic fallbacks - real, auditable model decisions.

    ApexYash11/Gatewise · Python

    20
    autonomous-agentsdecision-makingfastapigithub-appllmobservability
  • Judgments from TypeSafe Jev that read like Rust control flow: a yes/no is an if, a choice is an exhaustive match, a score is a comparison.

    pedro-pscunha/guideme-rust · Rust

    21
    api-clientasyncjudgmentllmobservabilityopentelemetry
  • A coding agent CLI where Jev (TypeSafe System One) or Laya decide what to do next and a configurable LLM does the work.

    thomasbrueggemann/jeffrey · TypeScript

    20
    clicoding-agentslayallm
  • Jev-style /v1/systemone API in front of any OpenAI-compatible LLM server (one-token logprob scoring, MIT)

    TOSUKUi/jev-bridge · Python

    21
    classificationinferencellmlogprobsopenai-compatiblesglang
  • Decisões tipadas para o código (TypeSafe Jev) e texto livre para pessoas (LLM). Custo zero por padrão.

    thiago-lage/jev-claud · Python

    20
    claudellmpython
  • Agent-facing command line for Jev, TypeSafe AI's System One model: ask typed questions, get calibrated probabilities. Unofficial, built on jev-sdk.

    portlandhodl/jev-cli · Rust

    21
    ai-agentsclillmrust
  • An evidence-graded deep dive into Jev (TypeSafe AI's System One model): interface, verification, reproduction comparison, and field guide. Bilingual (EN/中文), with runnable probe tools.

    LouisUltra/jev-deep-dive · Python

    20
    bilingualdecision-modeldeep-divellm
  • Runnable samples for Jev, TypeSafe AI's System One model. Send state and questions carrying their own answer options, then branch on the typed value that comes back.

    aarora79/jev-samples

    21
    calibrationclassificationcode-samplesconfidence-thresholdsdecision-makingexamplesllm
  • Agent Skill that finds where TypeSafe Jev decision models would pay off in a codebase. Works in Claude Code, Codex, Cursor and other Agent Skills hosts.

    PedroAlvarado/jev-scout · TypeScript

    20
    agent-skillsclaude-codeclaude-skillscodexllmtypescript
  • Jev vs GPT-4.1 as synthetic survey respondents on Twin-2K-500. How you ask mattered more than which model you used.

    jjd-lab/jev-synthetic-survey · Python

    20
    behavioral-economicsbenchmarkcalibrationdigital-twindigital-twinsllmllm-evaluation
  • Grounded information extraction that cannot hallucinate: code proposes spans, Jev decides. An open-source alternative to LangExtract, with a bilingual benchmark and paper.

    gabazureus/jevextract · Python

    21
    benchmarkgroundinghallucinationinformation-extractionlangextractllmnamed-entity-recognition
  • grep by meaning: pipe in any text, ask a yes/no question in plain English, get only the matching lines. Works behind tail -f, about $0.004 per 1,000 lines, powered by TypeSafe's Jev.

    allebee/jevgrep · Python

    20
    clicommand-line-tooldevopsgrepllmlog-analysis
  • A linting tool combining static analysis and Jev queries to help improve... Jev queries

    Fox-Islam/jevlint · Python

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

    suidouble/let-jev-speak · JavaScript

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

    AfnanHussain10/Memworthy · Python

    20
    agent-memoryai-agentsllmmem0memorypolicypython
  • 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
  • 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
  • 1054qualm
    Typed decisions from a System One model, where uncertainty is something you have to handle.

    qddegtya/qualm · TypeScript

    21
    classificationdecision-makingesmllmtype-safety
  • 1073tally
    Turn a pile of comments into an auditable distribution: Jev judges each item, code counts the percentages. React workspace + Python engine with pluggable data sources.

    adlternative/tally · Python

    20
    data-analysisi18nllmllm-evaluationpythonreact
  • Hands-on demos for TypeSafe's Jev (System One) model: six runnable examples and four field notes. Runs offline with no API key; samples/ holds real measured output from jev-1.13.0.

    ItBayMax/typesafe-ai-jev-example · Python

    20
    ai-engineeringclassificationllmpythonrag
  • 1093vd-jev
    VisiData plugin: ask a closed question about every row of a text column with a decision model (Jev or any other on OpenRouter) and get typed columns back: a probability, a label or a point on a scale, each with its confidence.

    ondata/vd-jev · Python

    20
    clidatadecision-modelllmopenrouterpythonterminal
  • Lints Jev requests before they are sent: offline checks for missing none-of-the-above options and broken state paths, then Jev itself for what structure cannot decide.

    suraj-phanindra/wellposed · JavaScript

    20
    agent-skillsai-toolingclaude-codecodexlinterllm
  • Independent, source-linked research on TypeSafe AI's Jev (System One), with 947 rubric-scored public repositories, recurring patterns, datasets, and bilingual documentation.

    g0runmezadam/what-is-jev · Python

    20
    ai-agentsbenchmarkbilingualclassificationdatasetdecision-modelllm
  • A curated guide to Jev, TypeSafe AI's System One decision model — selection advice, API-verified cookbooks, independent evaluations, and 100+ community. 中英双语

    dog-last/awesome-jev · Python

    12
    awesomeawesome-listchinesellmpython
  • Jev 优质应用与生态精选|System One 决策模型:开源应用·SDK·平台集成·开源复刻·教程 | curated apps & SDKs for TypeSafe AI's Jev model

    JingHao-Leon/awesome-jev-apps · Python

    11
    ai-agentsai-routingawesome-listchineseclassificationllmstructured-output
  • The Jev projects actually worth your time — picked, compared, kept current.

    charetterat/awesome-jev-essentials · Python

    10
    ai-agentsawesomeawesome-jevawesome-listdecision-modelllm
  • 1122bobcat
    Bobcat: a typed-decision model. State in, Choice / Noul / Score out, with a probability for every answer you name; no generated text. Compiler, server, training and evaluation code for Bobcat 1.1 and Bobcat Flash 1.1.

    foxl-ai/bobcat · Python

    10
    calibrationclassificationhuggingfacellmtyped-decisionsvllmpython
  • A precision-first RAG orchestrator: filters before it generates, verifies before it answers.

    david96182/cribrix · Python

    11
    agentic-ragdockerfact-checkingfastapihallucination-preventionlarge-language-modelsllm
  • 1136decide
    One client for every decision model: Choice, Score and Noul over Jev, OpenRouter, laya, MLX, CrossEncoders and LLM fallback

    gopaljigaur/decide · Python

    10
    classificationdecision-modellayallmmlxpythonrouting
  • Jev thinks. Your code acts. The open-source lab for Choice, Score & Noul decisions.

    mionax/decisionops · CSS

    10
    ai-evaluationcalibrationdecision-intelligencellmlocal-first
  • Jev-scored context compaction for DeepSeek Harness. Score every message by relevance to the current task instead of dropping the oldest, pin the tracebacks and constraints, and fall back to stock behavior on any failure.

    YYTbit/dsh-plugin-jev-compaction · TypeScript

    10
    context-compactioncontext-managementdeepseek-harnessdsh-pluginllmtypescript
  • Per-turn model and reasoning-effort routing for DeepSeek Harness, decided by one Jev choice question. Jev picks the candidate, a confidence gate falls back, and every turn appends a receipt that can be replayed at zero cost.

    YYTbit/dsh-plugin-jev-router · TypeScript

    10
    cost-optimizationdeepseek-harnessdsh-pluginllmmodel-routingtypescript
  • 1163ezjev
    Open 4B typed-decision model (Jev-style /v1/systemone): calibrated per-option probabilities from one prefill. Training, data generation and eval pipeline on HF Jobs.

    everettjf/ezjev · Python

    10
    benchmarkcalibrationdecision-modelfine-tuninghuggingfacellmlora

101–150 of 261