AnkiWeb addon 100971621
Predicts estimated completion dates and days remaining for each learning goal level using your review history, with locally configurable card types and level targets.
Open on AnkiWeb Find alternatives
active
No GitHub repository linked.
| Min Anki | Max Anki | Updated |
|---|---|---|
| 2.1.1 | 26.09.2+ | 2026-10-12 |
Loadingβ¦
Predicts remaining study time and finish time using an offline machine-learning model, with customizable progress displays, metrics, CSS styling, and fatigue alerts.
Turns exam dates into manageable daily new-card targets through multiple independent plans with flexible study days, previews, safe limit restoration, and automatic recalculation, while leaving review scheduling to Anki.
Calculates how many cards you must review daily to clear a chosen deck's due backlog, including subdecks, by a target date.
Converts Anki reviews into XP, levels, and streaks, letting users evolve one of 20 heroes, track progress with calendars and reports, and share holo cards.
Displays a customizable real-time dashboard in Anki tracking vocabulary and grammar progress across JLPT levels N5βN1, with study-pace completion estimates, exam countdown, and separate metrics.
Estimates how long today's Anki reviews will take and tracks live progress, pace, and remaining time across all decks based on recent average review times.
DDL Oracle answers one question: "How long until I reach my learning goal?"
Given your recent review history, it predicts a deadline (DDL) for each goal level in whatever subject you are studying. A new installation starts with a neutral task scaffold that tracks all decks as one card type, without any subject-specific curriculum. Add specific deck paths to split card types for language learning, exams, or custom curricula.
A small panel below the deck list, with one row per level:
Progress tracks cards assigned to each level by study history: a card is counted once it has at least one review-history entry. This is separate from mastery; a card does not need to reach the mastery interval threshold to be assigned to a level.
The prediction combines three signals taken straight from your revlog:
days_remaining = Ξ£ (gap Γ weight Γ expansion) / effort_per_day
No growth model, no retention factor β expansion empirically encodes
failures and relearning.
Tools β DDL Settingsβ¦ opens a 3-tab dialog:
* catches other decksWeights are auto-calibrated; you don't edit them by hand.
100% local. No network requests. Reads your collection.anki2 directly.
https://github.com/DGTOTOTO/DDL-Oracle