Skip to content

Jev Router — flaviusapop

Launchers for Claude Code, Codex, Grok CLI, and opencode that ask Jev which model-and-effort tier each human turn needs, rewriting only the model field while the real CLI runs unchanged.

Stars
7
Language
JavaScript
License
MIT
Published by
Community
Author
flaviusapop
Last verified
Oct 2026

flaviusapop/jev-router

User repository on GitHub

View on GitHub

Routes each turn in Claude Code, Codex, Grok and opencode to the cheapest model and reasoning depth that can finish it, using TypeSafe Jev

Forks
1
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

This is one of several Jev listings for the same project. The canonical entry is Jev Router — gargpratyush.

Languages
JavaScript
Platforms
CLI
Capabilities
Open sourceRequires API key

Highlights

  • One Jev call per human turn selects a tier as a (model, reasoning effort) pair; only the model field is rewritten.
  • Launchers reuse the CLI's existing login, so a Claude Pro, ChatGPT, or SuperGrok subscription works and no supplier key is needed.
  • The proxy binds to 127.0.0.1 only; your token is forwarded verbatim and never read, stored, or logged.
  • Guardrails: explicit model choices win, Jev failures keep the current model, and low-confidence answers never downgrade.
  • A Claude Code status line shows the routed model with Jev's confidence; JEV_DEBUG=1 logs the decisions.

Watch out

MIT, begun as a fork of gargpratyush/jev-router and now developing independently, as its NOTICE says. Two things leave the machine by design, the turn text to Jev and the request to its supplier, and JEV_DUMP writes whole request bodies containing prompts and code.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Hard-coded rules moved to Jev

YouTube: Joe Maddalone tries Jev as a routing and filtering step, with a transcript-analyzer demo.

Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.

FacebookClinicnotes

YouTube: Jev explained for routing and judging, with a comparison against LLMs.

Related terms

Glossary definitions related to this entry.

More Jev resources like this

8GitHub stars
A model router for the Codex CLI: on every user turn Jev judges how hard the task is and a YAML policy picks one of three lanes — flash, craft or forge — so premium quota goes to the prompts that need it.
Jev Agents & MCP#community#typescript#codex
59GitHub stars
A free Claude Code skill that puts Jev in front of the expensive model: thirteen commands sort, check, score, gate and verify with Jev, so Claude reads only the unsure slice and writes the output. Needs python3 and an OpenRouter key.
Jev Agents & MCP#community#python#claude-code
32.6kGitHub stars
A Claude Code configuration CLI shipping Jev modules for model routing, skill suggestion, tool guardrails, auto-mode gates, and sandbox hooks.
Jev Agents & MCP#community#typescript#coding-agent
21GitHub stars
Claude Code hooks that narrow a roster in YAML, ask Jev which handler owns a prompt, and log the band before anything is blocked.
Jev Agents & MCP#community#python#coding-agent
8GitHub stars
A Hermes plugin that routes every message you type to one of four model levels with Jev deciding in about 300 ms: lightweight for the trivial, maximum for what matters, and continuations stay on the model with the warm cache.
Jev Agents & MCP#community#python#hermes
0GitHub stars
MCP server and Claude Code plugin that files each captured note, link or meeting line with one Jev request: kind, project, action and duplicate questions answered in parallel. Routes to a project only at 0.45 or above, marks a duplicate only at 0.70 with a matching item, and stores text verbatim in append-only JSONL.
Jev Agents & MCP#community#mcp#note-taking
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai