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 “calibration”

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

  • 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
  • S1-Core — a zero-dependency Python harness for System 1 decision models (Jev & friends): choice/score/noul specs, fail-closed calibration gates, wave-parallel fan-out, replayable audit ledger.

    acbcore-labs/s1-core · Python

    10
    auditabilitycalibrationconformal-predictiondecision-modelinferencellm-harnessmachine-learning
  • 1528s1kit
    Test, calibrate and route System One decision models (Jev, Laya, kev, llama.cpp, Ollama) on your own data.

    Eliot5566/s1kit · Python

    10
    calibrationclidecision-modelgithub-actionslayallm-evaluationllm-routing
  • 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
  • The self-updating, trilingual directory of everything built on Jev (TypeSafe AI System One) — typed decisions, calibrated probabilities. AI-curated on free models.

    hdjekuue/awesome-jev · JavaScript

    00
    agent-harnessai-agentsai-safetyawesomeawesome-listcalibrationcontext-compaction
  • 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
  • Semantic ORDER BY for DuckDB, backed by TypeSafe AI's Jev model. Ships with independent calibration numbers.

    yodablocks/duckdb-jev · Python

    00
    brier-scorecalibrationduckdbexpected-calibration-errorllm-evaluationpythonsql
  • ¿Jev entiende tu acento? Pre-registered audit of TypeSafe AI's Jev on Spanish — accuracy, calibration and token cost — plus a CLI to run the same comparison on your own labelled data.

    marcosmartinez/jev-acento · Python

    01
    benchmarkcalibrationexpected-calibration-errorllm-evaluationnlppre-registrationreproducible-research
  • Evaluate typed AI decisions on labeled French-language cases.

    gbesse/jev-banc-francais · JavaScript

    00
    calibrationevaluationfrancejavascript
  • Measure 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

    00
    benchmarkcalibrationllmpython
  • Is TypeSafe AI's Jev calibrated? Reliability diagram, ECE and saturation split on 240 hand-labelled agent tool calls.

    themsquared/jev-calibration · Python

    00
    agentevalsagentgatewayai-agentsbenchmarkcalibrationllmpython
  • Independent calibration audit of TypeSafe AI's Jev: when it says 80%, is it right 80% of the time? Tested on EIA weekly petroleum reports against an LLM classifier via LangChain, with exact ground truth from EIA data.

    n9omi/jev-calibration-audit · Python

    00
    calibrationcommoditieseiaenergy-marketsforecast-verificationlangchainllm-evaluation
  • Production evaluation and gateway tooling for Jev and System One-compatible decision models

    gbesse/jev-decisionops · TypeScript

    00
    ai-evaluationcalibrationdecision-modelgatewaytypescript
  • Position paper: the Hidden-Markov and fuzzy primitives missing from TypeSafe AI's Jev and System-One decision models. Two lemmas, one principle (Deferred Crispification), one architecture (BSF-S1).

    dnakhoa/jev-deferred-crispification · TeX

    00
    texcalibrationfuzzy-logichidden-markov-model
  • Get coding agents to write Jev questions that work the first time: rules measured on 57 labelled suites.

    BarakChamo/jev-kit · JavaScript

    00
    agent-skillsai-agentsbenchmarkcalibrationclaude-codeclaude-code-pluginclaude-code-skill
  • A self-paced notebook course on Jev, typed AI decisions, calibration, and related models.

    Optimizer077/jev-learning-course · HTML

    00
    calibrationeducationjupyter-notebookmachine-learninghtml
  • Workflow orchestration for System One models. Batch, gate, trace, and calibrate thousands of typed Jev decisions.

    milan6190/jev-orchestrator · Python

    00
    asynciocalibrationorchestrationpythonstructured-outputs
  • Does ORDER BY over a Jev probability put rows in a defensible order? Independent ranking, calibration and invariant measurements of TypeSafe AI's Jev: passes six pre-registered gates on 360 labeled rows, fails four of six on graded product relevance.

    yodablocks/jev-orderby-bench · Python

    01
    benchmarkcalibrationduckdbinformation-retrievalllm-evaluationpythonranking
  • Evidence-gated registry of Jev question packs — curated questions, golden cases and measured evidence for Jev-compatible decision endpoints

    dtduc-git/jev-packs · Python

    00
    ai-testingcalibrationevaluationgolden-datasetllm-evaluationquestion-packspython
  • Fit act, review and escalate thresholds per question from labeled data with Jev; checks calibration. Stdlib Python.

    CapCurious/jev-threshold-lab · Python

    00
    calibrationdecision-modelpythonthresholds
  • Record/replay regression tests for Jev (TypeSafe System One) question packs — accuracy, calibration and cost gates in CI

    dtduc-git/jevassert · Python

    00
    calibrationcievaluationllm-evaluationpythonrecord-replaytesting
  • Deterministic decision runtime, zero-token caching, and certainty calibrator for TypeSafe AI (Jev).

    seb4ez/jevguard · Python

    01
    ai-agentscachingcalibrationdeterministicguardrailspippypi
  • How many decisions can a model make in a minute, and what do they cost? Jev, a System One decision model, raced against six LLMs on the same Snake boards.

    angelgalvisc/snake-arena-jev-vs-llms · Python

    00
    anthropicbenchmarkcalibrationdecision-makinglatencyllmmoonshot
  • Sorts customer support tickets automatically and sends the uncertain ones to a person.

    khaledjamal/support-ticket-router · Python

    00
    calibrationcustomer-supportdockerfastapigithub-actionshtmxllm-evaluation
  • Typed, calibrated decisions for Rust: a backend-agnostic client for System One models (TypeSafe AI's Jev), with cost-matrix decisions, caching, recording and calibration.

    heyaozh/system-one · Rust

    00
    api-clientcalibrationclassificationdecision-makingllmprobabilistic
  • TypeSafe's System One launch claims, each as a runnable experiment: Jev vs Claude vs keyword rules through one typed interface. Calibration, parallel questions, Wikiracing. Offline in CI; --live for the real thing.

    gsaini/system-one-models-getting-started · Python

    00
    ai-agentscalibrationclaudellm-evaluationpythonstructured-outputs
  • Run the new wave of decision models (Laya, Decider, Kev, Jev) side by side on your Mac. Structured input in, calibrated probabilities out, with honest accuracy, calibration, latency and memory numbers.

    jeffclimbsbikes/system-one-playground · TypeScript

    01
    apple-siliconbenchmarkcalibrationclassificationdecision-modelevaluationlaya
  • A semantic interrupt controller: calibrated semantic channels sampled over a live conversation at 5Hz, firing only on a hysteresis-gated edge. The model decides when; your code decides what. TypeSafe Jev + Deepgram Flux, zero dependencies.

    Saumya-patel-31/Thalamus · Python

    00
    ambient-computingcalibrationconversation-intelligencedeepgrammeeting-assistantpythonreal-time
  • Large typed decision model evaluation benchmark and novel calibration standard (`calibration.json`) for any typed decision inference system, covering 275 distinct use-cases and 27,598 individual decisions for Jev-like open typed decision models.

    kyr0/typed-decision-bench · Python

    00
    benchmarkbenchmark-frameworkcalibrationjev-alternativejev-api
  • Bench of typed decision models: Jev vs OpenJev vs Laya, small local LLMs and cheap hosted LLMs on the same zero-shot classification tasks, in English and French.

    4nt0ineB/typed-decision-bench · Python

    00
    benchmarkcalibrationenglishfrenchlayallm-evaluationmassive-dataset

51–81 of 81