Model routing with decision models

Deterministic evidence selector for noisy Codex investigations; its earlier Jev subagent router is kept for the record, not recommended.

Research code showing confidence cascades let a 0.8B prefill-only decision model approach a 4B model's accuracy at a fraction of the cost.

Research framework (DART) testing whether Jev's probabilities are a reliable signal to answer, escalate or abstain.

Open lab on using Jev routing in front of Claude Code correctly: measured bugs and patch, hard fallback, completion gate.

Chinese Slay the Spire 2 agent research: code handles rules, cheap Jev makes most choices, a stronger model takes key moments.

Stdlib-Python guardrail and model router for LLM gateways on Jev, with an independent accuracy, calibration and latency evaluation.

Chinese translation of 'Jev Engineering for coding agents', design notes on a harness where Jev makes every per-turn decision.

Juspay's TypeScript AI SDK with decide as a third inference type next to generate and stream, backed by Jev or Laya.

OpenAI-compatible LLM router across 80+ providers with an optional jev-auto mode that picks the model using calibrated probabilities.

Self-hosted Rust LLM gateway that puts OpenAI, Anthropic and Jev-style /v1/systemone backends behind one endpoint with load balancing.

Community .NET 10 SDK giving one API for choice, score and assessment over Microsoft-Decision-1, Ollama or native Jev.

Session-aware OpenAI-compatible gateway that routes chat requests by task type, scale and rigor, optionally via Jev Choice questions.

Per-turn router: one ~350 ms Jev call picks model tier, effort, tools and skill, with a hard deadline and regex fallback.

Go model-routing gateway for OpenAI and Anthropic clients where Jev picks a model from editable model cards, with CLI and dashboard.

LangGraph decorator that lets Jev take routing decisions it is confident about and falls back to your existing LLM router otherwise.

Chooses the model tier, skills and MCP servers for each coding-agent session with two Jev requests, then launches Claude Code or Codex.

Python client that sends one Choice/Score/Noul request down a fallback chain of hosted and local decision models with confidence gates.

Elixir client for System One decision models (Jev, Clef, OpenAI Decisions, OpenRouter, self-hosted) returning full distributions.

Federated knowledge retrieval engine for agents that uses Jev to route queries to backends and re-rank evidence, with keyword fallback.

Public wall where Jev answers short questions yes, no or it depends in about 100 ms and picks which LLM answers signed-in users.

Three Spanish-language demos where Jev decides and Claude reasons: Jira triage, code pre-flight and a PR review router.

Browser playground: configure a pool of OpenRouter models, let Jev pick one for a task, then judge whether its pick was right.

Small demo that routes a task to a research, code, browser, support or writer agent with Jev and shows a visual swarm map.

0.8B open System One model with task adapters that makes millisecond decisions in front of a larger local model like Qwen3.8-27B.

Dependency-free Python wrapper that turns any LLM API into a Jev-style choose-one-option decision call for old machines.

Gateway that distils System One or LLM answers into small fine-tuned classifiers and serves them when confident, falling back otherwise.

Clojure System One engine on Jolt that routes typed questions to Laya encoders, a llama.cpp 'thinker', Clef or TinyDecide.

Python tool that measures where to route decisions between Jev and a larger model on your own data, then routes by confidence.

Claude Code plugin that routes each prompt, step and subagent to the cheapest capable Claude model with effort caps and a live band.

CLI that fits per-question confidence thresholds to a target accuracy on your labelled data, reports escalation share and fails CI on drift.