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 for Elixir
An Elixir client that treats Jev as a peer GenServer: you reply with questions and its typed answers arrive as messages you pattern-match, with network-free tests.
- Category
- Repos & SDKs
- Published by
- Community
- Author
- dannote
- Added
- 2026-09-22
Tagscommunityelixirsdkclassification
Highlights
- Question shorthands are typed by criteria shape: a string is a Noul, a question and map tuple is a Choice, and a question and list tuple is a Score.
- Replies are plain maps with label atoms, expected score floats, probabilities, confidence, usage, and the concrete model that answered.
- The server never blocks on Jev: a hundred calls can be in flight and each answer finds its handle_answer/3 clause when it lands.
- Backends are swappable via the Jev.Backend behaviour, so a cascade can ask a local model first and escalate to Jev when confidence is low.
Quickstart
elixir
# mix.exs
def deps do
[{:jev, "~> 0.1"}]
end
# config
config :jev, api_key: System.get_env("TYPESAFE_API_KEY")Watch out
MIT-licensed. Requires Elixir 1.18+ and Erlang/OTP 27+ and a TYPESAFE_API_KEY, though a self-hosted model speaking the same wire format works without one.
More like this
475GitHub stars
A local server and Python package that runs open models with Hugging Face Transformers or PyTorch and returns Choice, Score, and Noul answers read from next-token logits instead of generated JSON.
Repos & SDKs#community#python#open-models
Communitysimple-jev
18GitHub stars
A RubyLLM 2 provider that adds Jev through structured output: build Noul, Choice, and Score questions with a schema builder, pass them to chat.with_schema, and read typed answers from response.parsed.
Repos & SDKs#community#ruby#sdk
Communityruby_llm-typesafe
7GitHub stars
An async LangGraph workflow that sends a mocked email to Jev, receives a typed Choice between invoice and general, and routes it to a demo handler, with confidence and both label probabilities printed for inspection.
Repos & SDKs#community#python#agents
Communitytypesafe-jev-workflow
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