Back to browse
Core Kanji, an SRS with no self-grading that picks what to study next

Core Kanji, an SRS with no self-grading that picks what to study next

by moxza·Jul 21, 2026·1 point·0 comments

AI Analysis

●●●BangerBig BrainNiche Gem

Grades by answer latency against your rolling baseline instead of making you self-report difficulty.

Strengths
  • FSRS memory state tracking with stability and retrievability metrics
  • Latency-based grading eliminates subjective self-assessment bias
  • Corpus frequency × word-completion algorithm picks optimal next item
Weaknesses
  • Limited to toy corpus demos; unclear path to full language learning content
  • Niche audience of SRS users who want algorithmic tweaks over UX improvements
Category
Target Audience

Language learners and students using spaced repetition systems

Similar To

Anki · SuperMemo · FSRS

Similar Projects

Developer Tools●●Solid

Argus – AI code review that doesn't grade its own homework

Independent review is the hook — the AI that writes the code isn't the one giving it a stamp of approval. It actually builds a structural map (tree-sitter + PageRank), uses hybrid embeddings + keyword search, and folds git-history heuristics into reviews that can be posted back to GitHub. It feels like a carefully thought-out, modular CLI tool, but adoption will hinge on robustness, prompt tuning, and real-world scale.

Big BrainSolve My Problem
meru143
115mo ago
Productivity●●Solid

Built and shipped an iOS app from my phone while traveling Japan

The real stunt here isn't the phrasebook — it's the developer workflow: a never-sleeping Mac + SSH + persistent shells to trigger remote TestFlight builds while living out of a backpack. The app is practical (offline, pre-generated ElevenLabs audio, dynamic-number phrases, JLPT kanji and one‑time IAP), so the demo isn't vaporware — it's a neat example of shipping under extreme constraints rather than a novel product idea.

WizardryNiche GemShip It
lordokami
205mo ago