Nicheloom visits: 58,301 all-time · 7,637 in the last 7 days

The opportunity tracker for new startups.

Today: 1,008 launches · Niche of the day: specialized calculation tools · See what launched today →

autojev

Full-weight Qwen decision model with calibrated probabilities, training code, REST API, and playground.

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

GITHUB · launched Sep 19, 2026 · 28 upvotes (top 29%) · 0 views

Niche: machine learning developer tools · 303 launches, 11 in the last 7 days ▼ -45% · Explore this niche →

Category and tags
  • Horizontal
  • Model & infra
  • Developer
  • AI-native
  • Hobby / open-source project
  • calibration
  • classification
  • pytorch
  • qwen

Visit website ↗ Source listing ↗

More like this: all 303 launches in machine learning developer tools →

Could you build this?

Partial While the inference API and playground are simple wrappers, the core artifact is a full-weight fine-tuned 27B parameter multimodal model trained on 73k curated decision examples with calibrated output probabilities.

What it would actually take: A real version requires an H100/H200 compute cluster or high-end cloud instances (vLLM/DeepSpeed/Axolotl/PyTorch), a curated decision/classification dataset of tens of thousands of domain examples, and post-processing calibration algorithms (e.g., temperature scaling). While vibe coding can assemble the training scripts and FastAPI/Gradio harness, model curation, fine-tuning infrastructure, and validation require ML engineering expertise and significant GPU resources.

Competitors

Other products that read as similar to this one : 2605 launches clear the similarity bar, closest 8 shown.

Attention rank: #718 of 2606 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 325 days after the earliest competitor.

  • tev1 · github · 2026-09-23 · 154 upvotes · similarity 0.79
  • Qev · github · 2026-09-29 · 11 upvotes · similarity 0.77
  • bev-train · github · 2026-09-27 · 39 upvotes · similarity 0.74
  • quyet · github · 2026-10-03 · 23 upvotes · similarity 0.74
  • decider · github · 2026-09-16 · 130 upvotes · similarity 0.69
  • vev · github · 2026-09-30 · 11 upvotes · similarity 0.68
  • ProbabilityBench · github · 2026-10-14 · 9 upvotes · similarity 0.68
  • Gutsy, a 0.8B Jev-compatible decision model that runs on your CPU · hn · 2026-10-01 · 9 upvotes · similarity 0.66

Related data

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.