Cost and rate control with decision models

Host-agnostic routing layer that picks model, effort and provider per round for coding harnesses from trajectory evidence.

DeepSeek Harness plugins that filter tool output, prune stale context and disclose skills progressively, with Jev or Laya judging what goes.

Claude Code mod where Jev judges each message's /effort level and offers a one-key switch for that turn.

Zero-dependency Node proxy that shadows Jev with local decision models and reports whether you can safely swap, per question and policy.

Local router for Claude Code and Codex that has Jev assess each new task, then pins a policy-chosen model and effort for the conversation.

Policy-driven router that sends each LLM request to the cheapest capable model tier, escalating when Jev finds a reason.

JS and Python library that selects and prunes agent tools and MCP schemas, using offline vector search or Jev with calibrated probabilities.

macOS computer-use loop that OCRs the screen, has Jev pick the next action from a short list, and clicks, at about $0.0002 a step.

Rust five-tier cascade router that sends prompts to Jev or an LLM, escalating only ambiguous requests.

Chinese-documented LLM gateway with virtual model routing, protocol conversion and a transparent Jev System One proxy.

Preview router for macOS Codex where Jev picks the GPT model and reasoning effort for each request through an isolated profile.

CLI that filters coding-agent subscriptions by quota and policy, then asks TypeSafe to rank the rest and pick a reasoning effort.

Patched Codex CLI where Jev reads task context mid-run and picks the next reasoning effort level and how long it should last.

Codex and Claude Code skills that narrow a repository locally and let Jev judge which candidate files the coding model needs.

Cost-, cache- and quota-aware LLM router that classifies each turn with a Jev-class model, prices every route, and checks cheap answers.

Effortlane: local router for native Codex on macOS that uses Jev to recommend model and reasoning effort per turn, with a Shadow mode first.

Pulumi example where Jev picks the best cloud region and modules per user location while code does pricing math and provisioning.

DeepSeek Harness plugin for budgeted, read-only GPT 'teacher' consults; Jev may only suggest when a consult is worthwhile.

Python router that has Jev classify Grok Bot requests before costly work, returning actions like reuse_cache, stop_retry or ask_human.

Experimental Hermes plugin returning routing plans: Jev rates task complexity, deterministic policy picks the cheapest eligible model.

Local proxy for Claude Code that uses Jev to pick model and effort per message, routing subagents but guarding the cached main chat.

Prototype per-call model router for Codex where Jev picks the GPT model and reasoning effort for each call via a local Responses proxy.

Local Anthropic-compatible proxy where Jev scores each Claude Code turn and simple work is routed to cheap or free 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.

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

Depth-crawling research agent where Jev makes every per-page relevance and next-link decision and an LLM only plans and writes.

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

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

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