Nicheloom visits: 66,946 all-time · 9,621 in the last 7 days

The opportunity tracker for new startups.

Today: 1,339 launches · Niche of the day: game save editors and managers · See what launched today →

astro-weights

Agent-driven weight edits for open models, as LoRA adapters

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.

Open-source Python library for small edits to open-model weights. Agent (Claude, local model or yours) works through MCP server; library compares edited model with base on same problems; edit saves as standard LoRA adapter or merges into GGUF. First adapter: Qwen3.8-27B, MATH-500 (n=500): about 30% fewer output tokens, accuracy −0.6 points (95% CI −2.6 to +1.4), no change detected.

PH · launched Nov 19, 2026 · 3 upvotes (top 8%) · 0 views

Niche: machine learning model training platforms · 31 launches, 2 in the last 7 days · Explore this niche →

Category and tags

  • Horizontal
  • Model & infra
  • Developer
  • AI-native
  • Hobby / open-source project
  • Open Source
  • Developer Tools
  • Artificial Intelligence
  • GitHub

Visit website ↗ Source listing ↗

Could you build this?

No The product depends on research-level ML work: editing weights of large open models, evaluating on benchmarks, and producing LoRA adapters that actually improve performance, which needs GPU compute and ML expertise.

What it would actually take: Would use PyTorch, Hugging Face Transformers/PEFT for LoRA, and llama.cpp/GGUF tooling, plus an MCP server to expose the editing loop to agents. The hard part is designing weight edits that measurably improve targeted capabilities without regressions, which requires ML research skill, evaluation harnesses, and substantial GPU hardware for running 27B-scale models.

Competitors

Other products that read as similar to this one : 115 launches clear the similarity bar, closest 8 shown.

Attention rank: #14 of 116 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 380 days after the earliest competitor.

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.