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
s1
A Rust derive layer for typed System One decisions: enums and structs become Choice, Score, and Noul questions with compile-time-checked, confidence-gated answers, plus a scriptable fake client for network-free tests.
- Category
- Repos & SDKs
- Published by
- Community
- Author
- AbdelStark
- Added
- 2026-09-22
Tagscommunityrustsdkconfidenceclassification
Highlights
- Derive macros turn enums into Choice and Score questions and structs into typed question sets; adding a variant breaks the match until handled.
- Policy maps confidence onto Verdict::Act, Review, or Escalate, with per-variant thresholds and a NoulPolicy for yes/no questions.
- HTTP is not in this crate: enable backend-typesafe-rs to use the published typesafe-rs client, or use s1-test::FakeClient.
- MSRV is 1.85 (edition 2024), and every crate in the workspace has #![forbid(unsafe_code)].
- The triage and moderation examples run entirely through FakeClient: no network call and no API key.
Quickstart
rust
#[derive(Choice)]
#[s1(instructions = "Which team should handle this ticket?")]
enum Department {
#[s1("Payment, invoice, refund, or subscription issues")]
Billing,
#[s1("Bugs, errors, or integration problems")]
Technical,
}Watch out
Dual-licensed under Apache-2.0 or MIT. The typed layer is a git workspace rather than a published crate, HTTP lives in the separate typesafe-rs crate, and live use needs TYPESAFE_API_KEY.
More like this
1GitHub stars
A community Rust client for Jev's System One API whose environment variables, defaults, retries, identification headers, and error kinds match the official Python and TypeScript SDKs.
Repos & SDKs#community#rust#sdk
Communitytypesafe-rs
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
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