Spaced Repetition Scheduling With Forgetting Curve Modeling

via “ebbinghaus-spaced-repetition memory decay scoring”

Send voice notes to Telegram → get organized knowledge base, tasks in Todoist, and daily reports. Persistent memory with Ebbinghaus decay, vault health scoring, knowledge graph. Runs on Claude Code + OpenClaw. 5/mo.

Unique: Implements Ebbinghaus decay as a first-class scoring mechanism integrated into vault health calculations, rather than as an optional plugin. Decay scores influence task prioritization in Todoist, creating a closed-loop learning system.

vs others: More scientifically grounded than simple recency-based sorting because it models actual human forgetting curves; more practical than Anki because it works on arbitrary notes rather than requiring flashcard format.

via “biological decay-based memory forgetting”

Most RAG setups fail because they treat memory like a static filing cabinet. When every transient bug fix or abandoned rule is stored forever, the context window eventually chokes on noise, spiking token costs and degrading the agent's reasoning.This implementation experiments with a biological

Unique: Uses biological forgetting curves (Ebbinghaus decay model) to probabilistically fade memories over time based on recency and frequency, rather than fixed TTL or LRU eviction. Decay is parameterized and continuous, not discrete, allowing smooth degradation of memory confidence.

vs others: More cognitively plausible than simple vector DB retrieval + fixed context windows; enables natural forgetting without explicit memory management, but trades determinism and recall accuracy (52%) for more human-like behavior.

via “fsrs scheduling for flashcards”

Voice-led, FSRS-scheduled flashcards from YouTube, PDFs, web, or text. Auto-graded quizzes.

Unique: Utilizes a unique implementation of FSRS that adapts in real-time to user performance, enhancing the effectiveness of study sessions.

vs others: More personalized and responsive than static spaced repetition systems, leading to better retention.

via “spaced-repetition-scheduling-with-content-integration”

Learn languages from native content.

via “spaced repetition learning algorithm”

A simple yet powerful spaced repetition system designed to help you remember more.

Unique: Utilizes a hybrid of the Leitner system and adaptive learning algorithms to personalize review schedules based on user performance.

vs others: More adaptive than traditional flashcard apps, as it customizes review intervals based on individual user performance.

via “spaced-repetition-scheduling-with-forgetting-curve-modeling”

Unique: Models individual learner forgetting curves and adjusts spacing intervals dynamically based on review performance, rather than using fixed spacing schedules; likely implements SM-2 or Bayesian variants to optimize retention efficiency

vs others: More efficient than fixed-interval review because it personalizes spacing based on individual forgetting rates, reducing review time while maintaining retention

via “spaced-repetition-scheduling-with-forgetting-curve-modeling”

Unique: Implements core spaced repetition without premium paywalls or proprietary algorithms — uses transparent, open-source-compatible scheduling logic that learners can understand and predict

vs others: Simpler and more predictable than Anki's complex ease factor system, but less sophisticated than Memrise's ML-based difficulty scaling that accounts for word etymology and semantic relationships

via “spaced repetition scheduling optimization”

via “spaced-repetition-scheduling”

via “spaced-repetition-scheduling-for-retention”

Unique: unknown — no documentation on whether implementation uses Leitner, SM-2, or custom algorithm; unclear if parameters are learner-adaptive

vs others: Comparable to Anki's spaced repetition but integrated into broader learning platform; likely less customizable than Anki's open-source algorithm

via “adaptive spaced-repetition scheduling”

via “retention-optimization-through-spaced-repetition”

via “spaced-repetition-scheduling-for-vocabulary-retention”

Unique: Integrates spaced repetition scheduling directly into native content consumption workflows rather than requiring learners to switch to a separate flashcard app. This keeps vocabulary review contextual and embedded in the learning experience rather than isolated.

vs others: More integrated than Anki (which requires manual card creation and export) and potentially more contextual than SuperMemory by anchoring reviews to original content sources. Reduces context-switching overhead compared to standalone SRS tools.

via “spaced repetition scheduling and review optimization”

via “spaced-repetition-scheduling-for-vocabulary-retention”

Unique: Integrates spaced repetition into the main lesson flow rather than as a separate flashcard app, enabling vocabulary review to be interleaved with contextual practice. Uses performance history to dynamically adjust review intervals rather than fixed schedules.

vs others: More integrated and contextual than standalone flashcard apps (Anki, Quizlet) and more scientifically-grounded than simple review reminders, but requires consistent engagement to maintain effectiveness

via “spaced-repetition-optimization”

via “spaced repetition scheduling”

via “spaced repetition scheduling”

via “spaced-repetition-scheduling”

via “spaced repetition scheduling and review algorithm”

Unique: Integrates spaced repetition as a core study workflow feature rather than an optional add-on. Likely uses SM-2 or Anki-compatible algorithm with server-side scheduling to ensure consistency across devices and prevent users from gaming the system by manipulating local timers.

vs others: More sophisticated than Quizlet's basic review mode (which doesn't optimize spacing) and comparable to Anki's algorithm, but simpler to use for non-technical learners since scheduling is automatic rather than requiring manual configuration.