https://github.com/ankitects/anki/commit/2d88e386dc389e50513870bdc4df64ef2f1ccff2
Category: Anki
-
New Features:
A new Experiments section has been added to the Preferences screen. This is intended to bring experimental features such as the new editor early to users for testing and feedback. By @Luc-Mcgrady in #5057
Update to fsrs-rs 6.6.1, bringing performance improvements. By @asukaminato0721 in #4956
An experimental rework of the editor by @abdnh in #4029 can be enabled from Preferences>Experiments. The main goal is to make it possible to integrate the editor into mobile clients. May affect addon compatibility.
-
That’s some old code in python that was reimplemented in Rust.
-
What’s Changed
New Features- Update to fsrs-rs 6.6.1, bringing performance improvements. By @asukaminato0721 in #4956
- Strip FSRS parameters from deck configs on export without scheduling by @chrislongros in #4721
- An experimental rework of the editor by @abdnh in #4029 can be enabled from Preferences>Experiments. The main goal is to make it possible to integrate the editor into mobile clients. May affect addon compatibility.
- A new Experiments section has been added to the Preferences screen. This is intended to bring experimental features such as the new editor early to users for testing and feedback. By @Luc-Mcgrady in #5057
-
-
Strip
fsrs_params_4/5/6from each deck config when exporting withwith_scheduling=falseand also add an clear_fsrs_parameters() helper function.https://github.com/ankitects/anki/commit/8a99c47639491f38cb146ce7748b7b08ad77431f
-
If a card is in a filtered deck (odid != 0), the post-sync reschedule only updates its odue and the card stays in the filtered deck — but it still updates mod/usn. The end result is that reviews on other devices get overwritten.
-
Security update.
-
rename_tag in qt/aqt/browser/sidebar/tree.py optimistically updates item.name/item.full_name before the backend validates. When validation fails (e.g. a name with a space), CollectionOp‘s default path shows the error but doesn’t roll the UI back, so the sidebar keeps displaying the invalid name while the stored tag is untouched.
-
Supports fractional intervals lengths for same day review prediction of probability !!
-
Using AI to generate Anki flashcards has evolved rapidly over the past couple of years. Here’s a look at how it started and where we are in 2026.
The Beginning: ChatGPT Prompts (2023)
The first to provide an Anki flashcard-generating ChatGPT prompt was Jarret Lee in this Anki forums post: Casting a Spell on ChatGPT: Let it Write Anki Cards for You. The idea was simple — give ChatGPT a structured prompt and it returns properly formatted flashcards you can import.
AnkiBrain Add-on
Shortly after, the AnkiBrain add-on was developed, integrating AI directly into Anki’s interface. This made it possible to generate cards without leaving the application.
Current Landscape (2026)
The ecosystem has exploded. Here are the main tools available today:
- AnkiDecks AI — upload PDFs, PowerPoints, Word docs, or even YouTube links and get flashcards generated instantly
- Ankify — turns notes, PDFs, and slides into export-ready Anki decks with card preview and editing before export
- NovaCards — uses LLMs to generate cards from class notes, with a companion Anki plugin for in-app generation
- AnkiAIUtils — AI-powered tools to enhance existing cards with explanations, mnemonics, and illustrations
- Agentic AI approaches — tools like Claude Code can now generate batches of contextualised cards by describing the pattern you want
- MCP interfaces — AI models can now interact directly with your Anki collection through MCP connectors
My Approach
I still prefer writing my own cards for deep learning, but AI-generated cards are great for:
- Quickly converting lecture notes or documentation into reviewable material
- Generating vocabulary cards in bulk
- Creating first-pass cards that you then refine manually
The key is to always review AI-generated cards before adding them to your collection. Bad cards lead to bad learning.
/root 