Full Jev Tutorial What it is, how you can build with it and what new applications it can unlock → 0:00 Intro → 0:34 Jev explained → 4:06 API setup → 5:59 Demo 1: Voice-controlled browser → 11:33 Demo 2: AI memory → 17:27 Demo 3: YouTube predictor
Jev Router
A Pi plugin that has Jev pick one model and one reasoning-effort level from a configured list at the start of a session, then keeps both pinned for the rest of it.
- Category
- Tools & Integrations
- Published by
- Community
- Author
- mejiasd3v
- Added
- 2026-09-22
Tagscommunityjavascriptroutingagentsvercel
Highlights
- Requires Pi 0.85.1 or newer, Node.js 22.19 or newer, and a Vercel AI Gateway key; installs with pi install npm:pi-jev-router.
- Model and effort are chosen in one evaluation: task fit picks the model first, then Jev selects the lowest sufficient allowed effort within it.
- Only listed, authenticated models are eligible and the fallback must be listed too; routes replace the default list rather than merging.
- The model stays pinned for the session; adaptive effort for Codex Astra is opt-in and uses append-only configuration_update items.
- Routing reads up to eight recent messages within 192,000 UTF-8 bytes; oversized tasks use the fallback instead of a partial task.
Quickstart
json
{
"jevRouter": {
"options": {
"openai-codex/gpt-5.6-luna": {
"description": "Small fixes, tests, and routine implementation.",
"thinking": "auto"
}
},
"fallback": "openai-codex/gpt-6-astra",
"timeoutMs": 5000
}
}Watch out
MIT-licensed. Needs Pi 0.85.1+, Node 22.19+, and a Vercel AI Gateway key; selected conversation text is sent unredacted to Vercel/TypeSafe and evaluations are billed separately.
More like this
425GitHub stars
A Python toolkit that installs nine plain SKILL.md files for Hermes, Claude Code, and Codex, letting Jev route models, filter retrieved passages, select skills, and choose bounded computer or browser actions.
Tools & Integrations#community#python#agents
Communityhermes-jev-skills
340GitHub stars
Standalone Android agent and React studio for Mobilerun, powered by Jev: Jev selects operations and observed targets, code rejects stale actions, and a CLI, execution traces, and latency measurements ship in the repo. No ADB connection required.
Tools & Integrations#community#javascript#agents
Communitymobile-jev
326GitHub stars
Wrappers for Claude Code and OpenAI Codex that ask Jev to choose a model tier for each fresh user turn while preserving each CLI's native interface, tools, sessions, permissions, and authentication. Ships as the jev-claude and jev-codex commands.
Tools & Integrations#community#javascript#claude-code
Communityjev-router
From the community
Posts from builders shipping with Jev right now.
Full Jev video tutorial
The case against Jev-scored compaction
This is a terrible compaction strategy that fundamentally doesn't understand how compaction and context management work. Seems like a lot of people are confused so let's break this down. 1. Compaction isn't a filter The role of compaction is to clean up history to keep the 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
Classifying rows in DuckDB
I made a DuckDB extension where you can use @typesafeai 's Jev to do quick classification of rows in any csv/parquet file or duckdb table about 10sec for 1k rows ~ better than using an LLM, way more ergonomic than a classifier game-changing for data analysis!
A playable 16-judgment demo
typesafe's jev is fun! live demo you can play with: typesafe-demo.val.run
AI multiple choice, not essay writing
WTF is Jev by @typesafeai? Here’s the tl;dr ELI5: Think AI multiple choice, not AI essay writing. It doesn’t chat. It makes decisions your software can act on: “Spam or not?” “Which tool should this agent use?” “Does this need a human?” The exciting part: roughly 200x faster Show more
Screening agent actions with Jev
Tested TypeSafe’s Jev (no-text, probability-only model) as an AI agent safety monitor. Checking each action first worked well caught most attacks with almost no false blocks, and much faster than Gemini.
@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