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
jcm-router
A local proxy between Claude Code and the Anthropic API that picks the model and effort level per message with Jev, routing subagents whenever cheap but gating main-chat switches on prompt-cache arithmetic.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- adarshmishra07
- Added
- 2026-09-22
Tagscommunitytypescriptroutingclaude-codegateway
Highlights
- An early version routed everything: over 309 logged requests it cost $106.73 against an $87.19 do-nothing baseline, a $19.53 loss.
- On every main-chat switch the response returned cache_read_input_tokens 0 and cache_creation_input_tokens 360370, rewriting the conversation at 2x input price.
- The dashboard prices every logged request twice: once as it ran and once on the model Claude Code originally asked for.
- A supervisor respawns the router with backoff and falls back to plain passthrough after three crashes inside 60 seconds.
- Runs on Bun at localhost:8787 with a dashboard on 8788, and bun run up refuses to start if either port is taken.
Quickstart
bash
git clone https://github.com/adarshmishra07/jcm-router.git
cd jcm-router
bun install
cp .env.example .env # put your TYPESAFE_API_KEY in .env
bun run up
env -u ANTHROPIC_API_KEY ANTHROPIC_BASE_URL=http://localhost:8787 claudeWatch out
MIT-licensed; needs Bun, a Claude subscription that Claude Code already logs into, and a TypeSafe API key, and while ANTHROPIC_BASE_URL points at localhost with nothing listening every request fails.
More like this
140GitHub stars
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.
Tools & Integrations#community#typescript#gateway
Communityjev-gateway
63GitHub stars
A local-first Herdr CLI that filters your agent subscriptions with fixed eligibility rules, then asks TypeSafe Jev to rank the remaining Cursor, Claude Code, Codex, or OpenCode options and pick a reasoning effort.
Tools & Integrations#community#typescript#cli
Communityagent-router
4GitHub stars
An experimental Codex CLI router where a local Responses proxy asks Jev one Choice per model call to select a host-available model and reasoning effort, while application-owned acceptance decides whether the task passed.
Tools & Integrations#community#typescript#codex
CommunityJev-Auto-Router
From the community
Posts from builders shipping with Jev right now.
Trading bot, one decision per block
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
A Claude session from 1M to 86K tokens
This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be Show more
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