Skip to content
JevDirectory.org
CommunityTools & Integrations161 starsVerified 2026-09-22

JevRouter

A router that turns models, subagents, skills, MCP tools, CLIs, and plugins into one candidate set Jev answers with a single typed Choice, while the router code owns availability, permissions, and confirmation.

Open github.comBillionsBobby/JevRouter
Category
Tools & Integrations
Published by
Community
Author
BillionsBobby
Added
2026-09-22
Tagscommunitytypescriptroutingagentscoding-agent

Highlights

  • Jev owns the decision probabilities while JevRouter owns availability, permissions, risk, and confirmation; filtered candidates are never re-normalized.
  • On 10 Toolathlon tasks predicting the first five tool calls, Jev serial hit 38% of positions versus 24% for DeepSeek V4.1 Flash, at 1.58 s per task.
  • A decompose plus thread strategy reached 44% hits and 69% overlap on MCP-Atlas; beam selection lifted batch hits from 28% to 36% with no extra provider calls.
  • route answers one question; plan maps steps 1..N in serial, batch, or decomposed strategies, with append-only receipts carrying provenance hashes.
  • Medium, high, and critical capabilities require confirmation, nothing executes implicitly, and require_verified_candidates can block unverified descriptions.

Quickstart

bash
npx --yes github:BillionsBobby/JevRouter agent start --agent codex
OPENROUTER_API_KEY="YOUR_API_KEY" npx --yes github:BillionsBobby/JevRouter route --provider openrouter \
  --request "Find original sources before summarizing" \
  --candidates '[{"name":"search_web","description":"Find web sources"}]'

Watch out

MIT-licensed. Needs Node.js 20+ and a TypeSafe or OpenRouter key that stays in the environment; the benchmark measures ordered routing predictions, not end-to-end task completion.

More like this

Reticle
815GitHub stars
An MCP server and agent skill that verifies coding-agent work by driving the real running app and returning pass, fail, or couldn't-tell verdicts with the file:line to fix; its listing frames the approach as Jev-style machine-native runtime perception.
Tools & Integrations#community#typescript#mcp
Communityreticle
pi-warden
132GitHub stars
Pi extension that supervises a coding agent with Jev judgments: it holds risky tool calls, checks writes against project Markdown rules, and feeds most issues back to the agent as a steer instead of interrupting you. The conscience is beta and off by default.
Tools & Integrations#community#typescript#guardrails
Communitypi-warden
Stanley
112GitHub stars
A Jev-first command-line coding agent: natural-language requests are routed by Jev to one of ten bounded review and triage workflows, and unsupported requests fall back to the Pi coding agent or a workflow Stanley stages for promotion.
Tools & Integrations#community#typescript#cli
Communitystanley-code
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

LLM-as-a-judge, sped up

Yuchen Jin
Yuchen Jin
Databricks
@Yuchenj_UW
·

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.)

Image
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 94 replies

Instant compaction with Jev

A Claude session from 1M to 86K tokens

Alex Volkov
Alex Volkov
CoreWeave
@altryne
·

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

Image
Image
tamara
tamara
@tamarajtran

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

Watch on X
Reply
Read 164 replies

Vercel's fx safety reviewer, 18x faster

Guillermo Rauch
Guillermo Rauch
Vercel
@rauchg
·

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply
Read 137 replies

Jev lands on OpenRouter

700 leads scored for $0.09