Skip to content
JevDirectory.org
CommunityTools & Integrations63 starsVerified 2026-09-22

Agent Router

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.

Open github.comnidhi-singh02/agent-router
Category
Tools & Integrations
Published by
Community
Author
nidhi-singh02
Added
2026-09-22
Tagscommunitytypescriptcliroutingcoding-agentclaude-code

Highlights

  • Eligibility rules run before semantic ranking: enabled models, quota, and a 40% reserve on shared accounts are applied locally.
  • Routing always calls TypeSafe, and each run sends the task text; recognizable credentials are rejected locally before the request.
  • Supports Cursor, Claude Code, Codex, and OpenCode through one router run command, using existing agent logins rather than provider keys.
  • Ships as a Herdr plugin via herdr plugin install nidhi-singh02/agent-router, and router run only launches from inside a Herdr pane.
  • Local usage snapshots, decisions, and session history stay on the machine; Node.js 20 or newer is required.

Quickstart

bash
git clone https://github.com/nidhi-singh02/agent-router.git
cd model-router
npm install
npm run build
npm link -w @agent-router/router
export MODEL_ROUTER_HOME="$HOME/Code/model-router/.model-router"
router run "implement the approved plan in docs/plans/billing.md"

Watch out

MIT-licensed and marked pre-release. Needs Node.js 20+, a TypeSafe API key with no fallback, at least one logged-in agent CLI, and Herdr to launch agents.

More like this

Fast Jev Compaction
6.2kGitHub stars
A Claude Code plugin and npm library that replaces transcript summarization with Jev keep-or-drop judgments, deleting stale tool calls and results while kept text stays verbatim.
Tools & Integrations#community#typescript#claude-code
Communityfast-jev-compaction
Distill
683GitHub stars
A Rust coding-agent harness and TUI that uses Jev to pick a model and effort, route bounded utility work, and decide what context to keep, with code constraining every choice and validating results.
Tools & Integrations#community#rust#coding-agent
Communitydistill
Jev Review
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
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A million judged questions

Inferring Jev's internals from 1,000 calls

iwashi / Yoshimasa Iwase
iwashi / Yoshimasa Iwase
@iwashi86
·

Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more

Reply
Read 2 replies

The open System One roundup

小墨同学
小墨同学
@xiaomovps
·

Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more

小墨同学
小墨同学
@xiaomovps

Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格

Image
Reply
Read 6 replies

The launch post

Trading bot, one decision per block

Classifying 1,500 real emails

vogel
vogel
Anomaly
@ryanvogel
·

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

Watch on X
Diogo Almeida
Diogo Almeida
TypeSafe AI
@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

Watch on X
Reply
Read 69 replies