HN Showcase
Back to browse
GitHub Repository
32 starsTypeScript

RSS reader that scores articles 0–10 with LLM before you open them

by makhal01·Mar 21, 2026·2 points·3 comments
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainSolve My Problem

LLM scores articles before you open them, learns from your feedback loop.

Strengths
  • •Tag-frequency aggregation builds structured preference profile from thumbs up/down
  • •Hardcoded technical profile calibrates scores against post-mortems, not listicles
  • •One-command Docker deploy with optional local Ollama, no database provisioning
Weaknesses
  • •AI RSS scoring is crowded—Feedly AI, Readwise Reader already do this
  • •Zero stars, zero forks suggests early stage with unproven scoring accuracy
Category
Productivity
Target Audience

Engineers and technical readers drowning in RSS feeds

Similar To

Feedly · Readwise Reader · Inoreader

Similar Projects

Developer Tools●●Solid

Treliq – PR triage CLI with 20 signals and optional LLM scoring

Deduping PRs and scoring them with 20 heuristic signals is a concrete, useful idea — especially the scope-coherence signal and embedding auto-fallback for providers without embeddings. The repo supports CLI, a persistent server, GitHub App integration and an explicit --model flag for provider flexibility, but it's still early and adoption/UX examples (ranked output, workflows) are thin — promising engineering scaffolding that needs real-world validation.

Niche GemSolve My Problem
chrismagno
103mo ago
Data●●Solid

GoldenMatch – Entity resolution with LLM scoring, 97% F1, no Spark

Fellegi-Sunter matching with active learning beats Dedupe.io on complex datasets.

Big BrainSolve My Problem
benzsevern
302mo ago