# nokia-applied-research/AnyJev

> Turns any LLM into a decision model with typed questions (choice, yes/no, score) that return real probabilities read from the next-token distribution, without training. L0 removes position and label-prior bias; L1 adds temperature calibration from 100-500 labels.

- Magnitude: 6.2 out of 10 — Early signal
- Stars: 278 total · +107 stars today, ≈ 208 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-09-21 · Last push: 2026-09-23
- GitHub: https://github.com/nokia-applied-research/AnyJev · Homepage: https://pypi.org/project/anyjev/ · Page: https://gitnova.dev/en/r/nokia-applied-research/AnyJev

## Useful for

- Route incoming requests to a handler with a thresholdable confidence instead of raw logits.
- Gate a proposed tool call by asking whether it is destructive or irreversible.
- Calibrate a yes/no question on 100-500 labeled examples to get a usable p_true.

## Why it’s here

- 107 stars so far today, about 208 expected by the end of the day.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 2 days old and already has 278 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #77.
- About 55 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: 41
- Issues and pull requests: 2
- Watchers: 6
- Average over the last week: 127 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 7
- Latest release: v0.0.2 (2026-09-21)

## Stars per day, last 4 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-23: 0, 12, 161, 107

## Spotted in now

- Top new repositories this week: #77

## Similar by description

1. **NandhaKishorM/laya** — 8.8 · Breakout · AI agents · Python · +923 stars today, ≈ 2,973 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. **kshetrajna12/reflex** — 2.1 · Early signal · Language models · Python · +3 stars today, ≈ 8 by evening
   An open decision model: given a state (text, JSON, or image) and typed questions, it returns calibrated probabilities over fixed answer options. Runs on top of Qwen3.5 and answers with numbers instead of free text.
   Full card: https://gitnova.dev/en/r/kshetrajna12/reflex.md
3. **featherless-ai/simple-jev** — 2.6 · Cooling · Language models · Python · +1 star today, ≈ 10 by evening
   A Python server that turns open Hugging Face LLMs into a classifier: it reads next-token logits and returns JSON with choices, rubric scores, or truth judgments without training a separate classifier head.
   Full card: https://gitnova.dev/en/r/featherless-ai/simple-jev.md
4. **y0usaf/pi-jev** — 1.0 · Cooling · AI agents · TypeScript · +0 stars today, ≈ 1 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
5. **malevrigns/agent-jev** — 6.0 · Early signal · AI agents · Python · +14 stars today, ≈ 88 by evening
   AgentJev-0.6B is a specialist decision model for AI agent loops: it takes unstructured state (diffs, traces, logs) plus typed questions and returns a probability distribution over options in a single forward pass with zero token decoding.
   Full card: https://gitnova.dev/en/r/malevrigns/agent-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 2026-09-23 11:19 UTC, updated every 30 minutes.