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-routing”

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

  • 🌳 Groot 1 — open typed-decision model. Calibrated choice/score/yes-no answers over 64k-token states, System One API compatible, with a pure Bend engine. Beats Jev on zero-shot Folha news (87.8% vs 85.8%) and typed decisions (75.3% vs 73.7%).

    leofmarciano/groot · Python

    143
    bendbend-langcalibrationdecision-modelllm-routinglong-contextmachine-learning
  • Typed model routing for OpenClaw agents, powered by TypeSafe Jev

    trietphan/jev-claw · JavaScript

    40
    ai-agentsllm-routingmodel-routingopenclawopenclaw-pluginjavascript
  • 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
  • 778JEV
    JEV 调研报告:TypeSafe System One 决策模型与开源对标(含原始核实记录)

    Chorylee7/JEV · Python

    30
    decision-modelllm-routingresearch-report
  • AI model routing for Codex subagents. Let Jev choose the model and reasoning effort for each mission, using your own task profiles.

    guilhem/codex-subagent-router · JavaScript

    20
    agent-orchestrationagentic-aiai-agentscodexcodex-pluginllm-routing
  • Finite-sample guarantees for Jev (TypeSafe's System One). Conformal risk control turns calibrated probabilities into certified routing thresholds; prediction-powered inference audits them. 2,412 decisions on CLINC150 for $0.23 — including the shift and prevalence cases where the guarantee breaks.

    nikkoxgonzales/jev-certify · Python

    10
    clinc150conformal-predictiondecision-modelintent-classificationllm-routingopenrouterprediction-powered-inference
  • Cheap fail-open semantic edge layer for Jev (TypeSafe System One): decision service + confidence policy + decision logging + blind eval harness + skill router over 1,000+ skills. Stdlib-only Python.

    SupremeDreamZ/jev-fastloop · Python

    10
    ai-agentsdecision-enginellm-routingpython
  • Open lab: Jev (TypeSafe System One) routing in front of Claude Code - measured bugs, patch, and a hard fallback with alerts

    Pasblinn/jev-lab · TypeScript

    10
    claude-codellm-routingtypescript
  • Measured cost, latency, accuracy and raw output: TypeSafe's Jev and 12 other decision models (OpenAI Decisions API, Clef, Decider, d1…) — reproducible

    WallerChen/jev-measured · Python

    10
    benchmarkdecision-modelllm-routingopenai-decisions-apipython
  • One-shot model and reasoning routing for Hermes Desktop. Manual control wins. Explicit upstream integration preview.

    PraveenKumarSridhar/jevgauge · Python

    10
    hermes-agentllm-routingpythonreasoning
  • 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
  • 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
  • thinkdial — per-task reasoning effort for Claude Code, decided by TypeSafe's Jev: main loop, Claude subagents and Codex delegations. Effort-only by design: model switches break the prompt cache.

    DmitryBMsk/thinkdial · TypeScript

    10
    claude-codeclaude-code-modllm-routingprompt-cachingtypescript
  • Jev (TypeSafe AI) as a System One decision layer for a multilingual EN/UZ/RU RAG helpdesk, with an independent benchmark

    rajantripathi/fastgate-jev · Python

    00
    ai-agentsevaluationllm-routingmultilingualraguzbek
  • Jev answers first; only the uncertain band goes to a stronger model, with a check that stage two really is stronger.

    CapCurious/jev-cascade · Python

    00
    cascadecost-controlllm-routingpython

1–15 of 15