# Contrastive-LM/CLM

> CLM is a class of System One language models trained contrastively to connect states and actions; the repo serves CLM-8B behind a TypeSafe-compatible API for fast agent decision-making.

- Magnitude: 5.9 out of 10 — Early signal
- Stars: 147 total · +0 stars today, ≈ 84 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-09-23 · Last push: 2026-09-24
- GitHub: https://github.com/Contrastive-LM/CLM · Page: https://gitnova.dev/en/r/Contrastive-LM/CLM

## Useful for

- Serve clm-serve and score urgency and department for incoming customer messages
- Rank answer candidates or tool names via engine.rank for best-of-N selection
- Fine-tune a CLM head on your own data to verify agent solutions

## Why it’s here

- 0 stars so far today, about 84 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 1 day old and already has 147 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #134.
- About 40 forks a day — people are taking the code.
- Recent forks include notable developers: @dorucioclea (311 followers).

## 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: 10
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 120 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 30

## Stars per day, last 5 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-24: 0, 0, 0, 156, 0

## Spotted in now

- Top new repositories this week: #134

## Similar by description

1. **receptron/laya** — 4.2 · Early signal · Language models · TypeScript · +0 stars today, ≈ 36 by evening
   TypeScript wrapper for running the open-source Laya System-1 decision model via ONNX Runtime: takes a state and typed questions, returns answers with calibrated probabilities in one forward pass.
   Full card: https://gitnova.dev/en/r/receptron/laya.md
2. **Rizzo-AI-Academy/rizzo-flow** — 3.3 · Cooling · Language models · Python · +0 stars today, ≈ 24 by evening
   A local-first implementation of the Jev idea: an LLM returns typed decisions (boolean, choice, score, numeric) with probabilities in a single forward pass, without generating tokens. Compatible with the TypeSafe HTTP API.
   Full card: https://gitnova.dev/en/r/Rizzo-AI-Academy/rizzo-flow.md
3. **deepopen-com/deepopen** — 6.5 · Early signal · Language models · Python · +0 stars today, ≈ 190 by evening
   Open-source non-autoregressive System 1 decision engine for typed decisions: returns typed answers (choice, score, noul) in a single forward pass across 100+ languages without generating text. Suited for classification, routing and…
   Full card: https://gitnova.dev/en/r/deepopen-com/deepopen.md
4. **vinnylarouge/jevlike** — 2.3 · Cooling · Language models · Python · +0 stars today, ≈ 17 by evening
   A small trainable model that picks one option from a changing list of text options in a single forward pass, an open alternative to TypeSafe's Jev. Aimed at developers who need fast classification or menu selection over variable option…
   Full card: https://gitnova.dev/en/r/vinnylarouge/jevlike.md
5. **ekzhang/openjev-sglang** — 2.6 · Early signal · Language models · Python · +0 stars today, ≈ 17 by evening
   HTTP server implementing the TypeSafe/Jev API for structured text classification on Qwen3.6-35B-A3B via SGLang; returns answer probabilities without generating a chain of thought.
   Full card: https://gitnova.dev/en/r/ekzhang/openjev-sglang.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 2026-09-24 06:23 UTC, updated every 30 minutes.