Sieve by Fendora
AI that filters security scanner false positives
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.
Security scanners produce 80-90% false positives. Engineers stop looking. Real vulns hide in the noise. Sieve is an ML filter trained on 1,442 labeled findings across 26 repos. It scores each Semgrep finding and posts only the real ones as a PR comment. - 95% precision on unseen repos - 4 lines of YAML, zero config - Learns from feedback - Open source (Apache 2.0)
PH · launched Oct 24, 2026 · 1 upvote (top 67%) · 0 views
Niche: application and system security scanners · 263 launches, 32 in the last 7 days ▼ -16% · Explore this niche →
Category and tags
- Security
- Agent / copilot
- B2B
- AI-native
- Commercial product
- Developer Tools
- GitHub
- Security
Visit website ↗ Source listing ↗
More like this: all 263 launches in application and system security scanners →
Could you build this?
Partial The GitHub integration and PR commenting are vibe-codeable, but the core value is an ML classifier trained on 1,442 labeled findings. Reproducing that precision requires a comparable labeled dataset and ML expertise.
What it would actually take: A real version needs a labeled dataset of security scanner findings with true and false positive annotations, ideally across many repos. It also needs feature engineering on Semgrep output and code context, model training with careful evaluation on unseen repos, and a serving layer wired to GitHub Actions and PR comments. The main hard part is the labeled data and the ML evaluation discipline, not the integration.
Competitors
Other products that read as similar to this one : 47 launches clear the similarity bar, closest 8 shown.
Attention rank: #21 of 48 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 333 days after the earliest competitor.
- sieve · github · 2026-10-10 · 12 upvotes · similarity 0.41
- AI-powered Lie Detector · ph · 2026-09-22 · 1 upvotes · similarity 0.40
- Osuite: Anomaly detection · ph · 2026-10-29 · 2 upvotes · similarity 0.39
- Sift · ph · 2026-09-23 · 1 upvotes · similarity 0.39
- Artificial Detect · ph · 2026-10-16 · 1 upvotes · similarity 0.38
- Fake Checker KI+ · ph · 2026-10-11 · 1 upvotes · similarity 0.38
- AI-Based-Fake-News-Detection-System · github · 2026-10-02 · 8 upvotes · similarity 0.38
- SIGMA_Rules · github · 2026-09-30 · 10 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.