Model routing with decision models

Single-file Python proxy that asks Jev which model tier each Codex turn needs, rewrites the model, and escalates on failures.

Jev Router for Cursor: Jev picks a COST, BALANCED or INTELLIGENCE tier per task, with soft routing in chat and hard routing via the SDK.

Three Italian-language Claude Code prompts that build Jev-powered model routing, context compaction and code review into your project.

Multi-agent Codex factory: Jev decides task shape, decomposition and routing, and failures are classified, not blindly retried.

Gateway that batches agent control questions through Jev and calls a generative LLM only when policy says generation is needed.

Offline-by-default demo of six Jev decision workflows: model tiering, prompt screening, tool-call risk, reranking and more.

Experimental plugin wiring Jev into coding-agent harnesses to pick skills, tools, models and browser moves, starting with OpenCode.

Self-hosted LLM gateway with semantic cache, privacy sandbox and a 'Jev classifier' tiering requests across cheap and frontier models.

Python CLI that shows which OpenAI model Jev would route a query to, independently reviewed by a local Ollama model.

Web chat where one Jev Choice picks nano, fast, balanced or frontier model tier per message via the Vercel AI Gateway.

Python router where Jev classifies prompt difficulty and stakes, then confidence-gated rules choose an OpenAI model tier.

Claude Code hook and skill (German docs) where Jev picks the cheapest sufficient Claude tier and whether to delegate to a subagent.

Claude Code plugin that routes every subagent spawn through Jev to pick its model, effort and tool profile.

Support-ticket triage pipeline where Jev scores every ticket and Python decides whether a general LLM should write a reply.

Guide and small prototype for using Jev with Herdr to route tasks to coding agents like Claude, Codex and Hermes under code-owned policy.

CLI that asks Jev which AI app should handle a task (Claude, ChatGPT, Cursor or Antigravity), then opens it and pastes the prompt.

Open-source LiteLLM-based router where clients send one model id and Jev picks which model serves each request.

Databricks App that uses a Jev Choice over named routing options to pick which Foundation Model endpoint answers each message.

Routes each subagent task to the cheapest model smart enough for it, using Jev to rate task difficulty from low to max.

Imports agent traces from LangSmith, Langfuse or OpenTelemetry and tests whether a smaller decision model can make routine choices.

Local-first, outcome-aware model router for coding harnesses that picks a capability tier per task with Jev and learns from history.

Launchers for Claude Code and Codex that use Jev to pick a model tier for each new user turn while keeping native tools.

Rust template for multi-agent orchestration with Jev as the L0 layer for typed routing, risk and escalation decisions.

OpenCode V2 plugin that asks Jev if a prompt is deterministic and, if so, skips chain-of-thought with temperature 0 and a short answer.

System 1 ingestion gate that asks Jev intent, risk and sensitivity in one call, then blocks, answers deterministically or passes to an LLM.

Claude Code skill that splits work into PBIs for Codex, Antigravity or Claude sub-agents, using Jev for model choice and triage.

Router that asks Jev or another classifier how much reasoning effort each coding-agent step needs, without breaking the prompt cache.

Experimental task router that uses Jev, skill profiles and environment checks to send requests to a rule, a skill or a large model.

Browser studio and templates for trying Jev as a System 1 reflex gate in front of frontier LLMs, with code exporters.

ComfyUI custom node that asks Jev noul, choice or score questions inside image-generation workflows, e.g. to pick a workflow template.