After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x Show more
jev-gateway
A local gateway for coding agents that asks Jev which tool to call each turn and steers the LLM when Jev is confident, while every other request goes to your usual provider untouched.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- vinilana
- Added
- 2026-09-22
Tagscommunitytypescriptgatewaycoding-agentclaude-codecodexopenrouter
Highlights
- Launchers jev-codex, jev-claude, jev-opencode, and jev-gemini pass arguments through and work with subscription logins as well as API keys.
- When Jev is down, slow, or the key is wrong, every request goes straight to the LLM; the gateway never fails a request.
- Jev keys can come from TypeSafe, OpenRouter, or Vercel AI Gateway; the first launcher asks once and stores the choice in ~/.jev-gateway/.env.
- A dashboard at localhost:8790 shows routing status, Jev latency, confidence, cost, and LLM token counts; baseline mode compares with routing off.
- Listens on 127.0.0.1 only, leaves ~/.codex, ~/.claude, and ~/.config/opencode unchanged, and defaults to ports 8790, 8789, 8791, and 8788.
Quickstart
bash
npm install -g jev-gateway
jev-codex --dashboardWatch out
MIT-licensed and not affiliated with TypeSafe. Needs Node.js 22.15+ and a Jev key; only sessions started through the jev- commands are routed.
More like this
201GitHub stars
A local-first MCP server that gives Claude Code, Codex, Cursor, and OpenCode structured quality scores from Jev across correctness, complexity, tests, security, and other dimensions while the agent writes code.
Tools & Integrations#community#typescript#mcp
Communityjev-review
63GitHub stars
A Jev-guided context compaction library for coding agents: instead of summarizing old context, Jev decides which tool calls and results still matter while user and assistant text is kept verbatim.
Tools & Integrations#community#typescript#compaction
Communitysave-token-jev-clean
From the community
Posts from builders shipping with Jev right now.
The launch post
Trading bot, one decision per block
I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → jev-trader.vercel.app
Classifying 1,500 real emails
this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Fast browser use with Stagehand
we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
LLM-as-a-judge, sped up
Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Instant compaction with Jev
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant