# disler/ten-levels-of-jev

> A lab of ten levels showing how to use Jev (TypeSafe System One) for typed, probabilistic decisions in code and inside the pi coding agent, from a single yes/no gate to agent-chosen questions.

- Magnitude: 4.6 out of 10 — Early signal
- Stars: 101 total · +34 stars today, ≈ 42 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-09-27 · Last push: 2026-09-27
- GitHub: https://github.com/disler/ten-levels-of-jev · Homepage: https://youtu.be/_U-O5lYhJ7Q · Page: https://gitnova.dev/en/r/disler/ten-levels-of-jev

## Useful for

- Gate prompt injection in incoming messages with a noul question and a probability threshold
- Route agent requests to the right model or intent with a cheap choice call
- Add guardrail hooks to a coding agent's bash and write tool calls

## Why it’s here

- 34 stars so far today, about 42 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 2 days old and already has 101 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #169.
- About 15 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 26
- Issues and pull requests: 5
- Watchers: 1
- Average over the last week: 36 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 2

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-09-27 … 2026-09-29: 4, 63, 34

## Spotted in now

- Top new repositories this week: #169

## Similar by description

1. **NandhaKishorM/laya** — 4.1 · Cooling · AI agents · Python · +549 stars today, ≈ 671 by evening
   Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.
   Full card: https://gitnova.dev/en/r/NandhaKishorM/laya.md
2. **ryana/jevify** — 0.0 · Cooling · AI agents · +0 stars today, ≈ 0 by evening
   A set of prompts for coding agents that helps investigate what TypeSafe's structured decision model Jev could enable in an existing project.
   Full card: https://gitnova.dev/en/r/ryana/jevify.md
3. **ollaya-dev/ollaya** — 5.5 · Early signal · Language models · Rust · +63 stars today, ≈ 79 by evening
   A local runtime for decision models: pulls and serves classification and routing models behind a TypeSafe-compatible API. Like Ollama, but for models that return probabilities instead of text.
   Full card: https://gitnova.dev/en/r/ollaya-dev/ollaya.md
4. **typesafe-ai/skills** — 2.3 · Cooling · AI agents · +29 stars today, ≈ 36 by evening
   Agent skills for building with TypeSafe's System One API: typed decisions and probabilities for LLM agents. Installs as a Claude Code plugin or via skills.sh.
   Full card: https://gitnova.dev/en/r/typesafe-ai/skills.md
5. **y0usaf/pi-jev** — 0.4 · Steady · AI agents · TypeScript · +0 stars today, ≈ 0 by evening
   An extension for the Pi coding agent that adds a TypeSafe Jev decision layer: it judges bash/write/edit calls before they run and inspects command output, returning typed probabilities instead of prose.
   Full card: https://gitnova.dev/en/r/y0usaf/pi-jev.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-29 19:52 UTC, updated every 30 minutes.