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 ↗
More like this: all 31 launches in machine learning model training platforms →
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.
- Cline Desktop App · ph · 2026-09-11 · 257 upvotes · similarity 0.44
- frontier-weight-edit · github · 2026-11-03 · 28 upvotes · similarity 0.44
- Tracer: Fable-level AI at 1/3 the cost using open-weight models · yc · 2026-07-31 · 18 upvotes · similarity 0.38
- Gambit, an open-source agent harness for building reliable AI agents · hn · 2026-01-16 · 91 upvotes · similarity 0.38
- Kilroy · hn · 2026-04-16 · 5 upvotes · similarity 0.38
- Loras AI · ph · 2026-11-07 · 1 upvotes · similarity 0.37
- 20x · hn · 2026-02-26 · 6 upvotes · similarity 0.37
- blender-agent-sdk · github · 2026-10-17 · 16 upvotes · similarity 0.37
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.