Changelog - esper

Version 1.3.6

January 7, 2026

✨ New Features

Added LFM2.5 and LFM2.5 VL models.

Version 1.3.5

January 5, 2026

✨ New Features

Added indicators for loading and unloading local models.
Added search and sorting options to the chat model selection screen.
Added new preferences for turning auto scrolling message streaming on and off.
Added new preferences for using last used model for new chats rather than the default model.
Updated voice mode to start immediately on streaming instead of waiting for the entire message to be generated.

🐛 Bug Fixes

Fix bug causing downloads to show over 100%.
Fix Ministral 3 model not working.

Version 1.3.4

December 26, 2025

🐛 Bug Fixes

Fix many animation issues throughout the app causing crashes and other issues.
Redo shortcuts to single option with multiple parameters.
Make enter key submit messages instead of adding new lines.

Version 1.3.3

December 17, 2025

✨ New Features

Optimized RAG parameters for better accuracy and performance, especially for online models.

🐛 Bug Fixes

Temporary patch for local models not running on iOS 26.2.

Version 1.3.2

December 13, 2025

🐛 Bug Fixes

Fixed several issues with the new knowledge bases feature, including general accuracy issues, downloading and management of embedding models, issues with documents being or not being present in RAG retrieval, and using a new OCR engine for PDFs.

Version 1.3.0

December 12, 2025

✨ New Features

Knowledge Bases (RAG): You can now create knowledge bases (RAG) to use with your models. This allows you to upload documents and use them as context for your models. This is a great way to get more accurate responses and improve the quality of your conversations based on collections of information on personal information, work documents, recipes, domain specific information, or anything else.
Shortcuts: You can now create shortcuts that open in esper. This allows you to create custom commands that you can use to send information to your models.
New Models: Added Mistral Ministral 3 and Ministral 3 reasoning.
Many small UI and UX improvements & fixes.

🐛 Bug Fixes

Fix GPT OSS chat template bug.
Fix chat not scrolling to bottom in rare cases.

Version 1.2.4

December 1, 2025

✨ New Features

Major code refactor and optimization. This allowed for some optimizations and fixes like: major initialization speed improvements for both online and offline models, streaming fixes with some providers, and more.
Introducing esper Pro! A new one time purchase allows you to download more than one offline model at a time and also gives access to theme customization and more. Anyone who has already purchased the app or downloaded before December 1st will automatically be upgraded to Pro for free. This will allow us to continue to support the app and add new features in the future!
Added new GPU Acceleration option for offline models. This allows you to choose between faster GPU inference and more battery efficient CPU inference.
Added new toggle for resetting advanced parameters between chats. This allows you to turn it off so that params are saved everytime you edit them and then applied to any new chats you create.
Moved these two new settings and other preferences into their own settings menu screen.
Updated licenses page.

🐛 Bug Fixes

Fixed an issue causing the app to overload RAM when downloading large models, sometimes causing it to crash.
Fixed several error message issues and improved error handling.

Version 1.2.3

November 21, 2025

✨ New Features

Added locale selector for voice mode.

🐛 Bug Fixes

Gemini 3 Pro and Gemini 3 Pro Image (Nano Banana Pro) fixes.

Version 1.2.2

November 13, 2025

✨ New Features

Voice mode 🎤. Talk with any model using your voice.
Updated Google Gemini API support. More thinking controls on relevant models, more file upload options, Google web and Google maps search grounding, automatic url retrieval.
Updated xAI Grok search options. Select between searching the web or X (or both).
New models: Qwen3 VL vision model variants and IBM Granite text model.
Better conversation search. Search now keyword matches over messages as well as chat titles.

🐛 Bug Fixes

Various small fixes and improvements.

Version 1.2.1

October 13, 2025

✨ New Features

Added Apple Foundation model support.
Added TTS voice selection.
Added local model verify button. This feature makes sure the local model and filesystem are in sync.

🐛 Bug Fixes

Various small fixes and improvements.

Version 1.2.0

September 18, 2025

✨ New Features

Major framework and package updates.
iOS 26 upgrade support.
Complete refactor of the underlying chat UI, increasing performance and stability.
Added image generation support for OpenAI, xAI, OpenRouter, and Google API providers.

🐛 Bug Fixes

Fixed an issue where the interface would be very slow with large conversations.
Fixed accessibility issues with the switches in the Share With AI screen.
Fixed an issue causing Liquid AI LFM2-VL models to not work.
Fixed an issue causing the app to slow when deleting or downloading local models.
Fixed an issue with long system prompts not being editable in the My GPTs screen.
Fixed an issue causing assistant messages to copy plain text instead of full markdown.
Fixed an issue causing message generations intentionally stopped by the user to not be saved.