🆕 Windows v8 | macOS v5.5

🪟 Release notes for the Windows version (v8 🆕🎉):

Hey everyone! I got really busy for a while, but I'm now super excited to be back to updating Writing Tools :D
This is just the start of a lot of cool stuff that's on the To Do list!

1. ✨New updated Gemini / Gemma models! Fixes any "quota exceeded" errors.

Overnight, Google slashed usage limits on the free Gemini API.

• Writing Tools used the slightly outdated 2.0 model family, which got booted off the free tier (thus the errors).
• 2.5 Flash and 2.5 Flash Lite are slashed to a tiny 20 requests per day (welp!)

However, I've found a great solution/loophole! Turns out the Gemma models (also hosted on the Gemini API) are free for ~unlimited usage! And these are about the same (if not a little better than) Gemini Flash :)

Writing Tools now defaults to using Gemma 3 27B, which is a very, very intelligent model that runs incredibly quick and is notably more intelligent than the previous Gemini Flash model!

Writing Tools also has a new Custom Gemini model option, so you can choose your own Gemini model regardless of what the dropdown lets you choose.

2. 🔒 Improved security for on-device Gemini API key storage

Your Gemini API key was always safe and never sent anywhere except straight to Google, and was stored only on your local device in your config.json file.
To further bolster security, I now store your API key heavily encrypted with a custom encryption algorithm.
This way, if you ever happen to get malware that tries to search your entire hard drive for API keys, your Gemini key will be safe.

3. ⬆️ New Easy Update Logic!

You simply need to drag and drop the new Writing Tools.exe to replace your old one!

On first launch, if you'd been using Gemini before, it'll automatically migrate you to the new Gemma 3 27B model and also encrypt your previously saved Gemini API key :)

Upcoming features:

• Per-button hotkeys and model choice
• Significantly improving stability on all PCs
• Localization (multi-language UI) — @momokrono has built the entire framework for this, and my gratitude is unbounded — this would help so many. It'll be ready by the next release!
• Checking that the active window is the same before pasting.
• And more! See my Windows/Linux Version Feature Roadmap!

Known Issues

1. On some devices, Writing Tools may not work correctly with the default hotkey.
   To fix it, simply change the hotkey to ctrl+` or ctrl+j and restart Writing Tools.
   PS: If a hotkey is already in use by a program or background process, Writing Tools may not be able to intercept it. The above hotkeys are usually unused.

2. The initial launch of the Writing Tools.exe might take unusually long — this seems to be because AV software extensively scans this new executable before letting it run. Once it launches into the background in RAM, it works instantly as usual.

---

---

---

🍎 Release Notes for the macOS Version by @Aryamirsepasi (v5.5):

• Added text size persistence in response view by @gdmka
• Fixed OpenAI-compatible API failure with custom Base URL by @drankush
• Liquid glass support on macOS 26+
• Updated Google Models similar to Windows v8
• Improved Markdown support on Response Window with LaTeX support

Please Note:
After updating the macOS version, the tools may sometimes not show up.
To fix this, re-enable accessibility access:

System Settings → Privacy & Security → Accessibility → Select WritingTools → Press the minus (–) button → Press the plus (+) button → Add WritingTools again and enable access.

Windows v7.1 | 🆕 macOS v5.4

🎉 Release notes for the Windows version (v7.1):

v7.1 Hotfix Additions:

• Fixed an issue with the OpenAI Provider, and improved & optimised the entire AI Provider architecture.
• Improved the thinking text animation.
• Fixed the default icon arrangement to be the same as v6.

v7 Additions:

1. Customizable buttons! You can now add, edit, remove, and rearrange the buttons.

Huge thanks to @momokrono for building the entire back-end for this 💛! I added the GUI (with draggable buttons, reset to default functionality...).

2. Sleeker pop-up UI

3. A native Ollama AI Provider (using the Ollama API), for easier Ollama setup & custom model-in-memory-time options — entirely thanks to @momokrono!

4. New Gemini model options, with better explanations

5. A new Pause & Resume option to stop Writing Tools from reading your hotkey if necessary. Again, @momokrono so awesomely implemented this :D

5. Other Improvements:

• UX improvements to the Summary etc. pop-up window (optimized initial height)
• Friendlier error message on hitting Gemini rate-limits
• Added graceful quitting when running through the terminal [credit: @momokrono]

I want to thank @momokrono once again for all his help and support—not only in contributing code, but also for extensively helping manage GitHub issues. Thank you, truly—I'll never forget your kind contributions. 💛

Upcoming features:

• Localization (multi-language UI) — @momokrono has built the entire framework for this, and my gratitude is unbounded — this would help so many. It'll be ready by the next release!
• Hotkeys for specific options.
• Support to remove reasoning token markers if needed (PS: DeepSeek R1 & Gemini 2.0 Thinking already work!).
• (researching) Tracked changes/diff check (to compare proofread text with the original).
• Checking that the active window is the same before pasting.
• More feature suggestions on GitHub Issues, and potentially future ones.
• And of course, bug fixes and improvements overall :]

⬆️ Update Instructions:

You can keep using your old config.json to preserve your set-up! Simply bring it over into the new Writing Tools v7.1 folder you'll download below.

🐞 Known Issues

1. On some devices, Writing Tools may not work correctly with the default hotkey.
   To fix it, simply change the hotkey to ctrl+` or ctrl+j and restart Writing Tools.
   PS: If a hotkey is already in use by a program or background process, Writing Tools may not be able to intercept it. The above hotkeys are usually unused.

2. The initial launch of the Writing Tools.exe might take unusually long — this seems to be because AV software extensively scans this new executable before letting it run. Once it launches into the background in RAM, it works instantly as usual.

---

---

---

🆕🎉 Release Notes for the macOS Version by @Aryamirsepasi (v5.4)

• Improved UI across the app
• Improved Accessibility
• Implemented Fixes for Issues #231 , #227 (new fix attempt in 5.4), #224
• Improved Code
• Fixed a lot of Bugs
• Search in Icon Picker
• New Icon and some Liquid Glass elements for macOS 26
• New MLX Models (Gemma 3n, Qwen3 VL)
• Added Keychain Support for more secure key storage
• Improved iCloud Support
• Updated to use the new mlx-swift-lm package

Please Note:
After updating the macOS version, the tools may sometimes not show up.
To fix this, re-enable accessibility access:

System Settings → Privacy & Security → Accessibility → Select WritingTools → Press the minus (–) button → Press the plus (+) button → Add WritingTools again and enable access.

Windows v7.1 | 🆕 macOS v5.0

🎉 Release notes for the Windows version (v7.1):

v7.1 Hotfix Additions:

• Fixed an issue with the OpenAI Provider, and improved & optimised the entire AI Provider architecture.
• Improved the thinking text animation.
• Fixed the default icon arrangement to be the same as v6.

v7 Additions:

1. Customizable buttons! You can now add, edit, remove, and rearrange the buttons.

Huge thanks to @momokrono for building the entire back-end for this 💛! I added the GUI (with draggable buttons, reset to default functionality...).

2. Sleeker pop-up UI

3. A native Ollama AI Provider (using the Ollama API), for easier Ollama setup & custom model-in-memory-time options — entirely thanks to @momokrono!

4. New Gemini model options, with better explanations

5. A new Pause & Resume option to stop Writing Tools from reading your hotkey if necessary. Again, @momokrono so awesomely implemented this :D

5. Other Improvements:

• UX improvements to the Summary etc. pop-up window (optimized initial height)
• Friendlier error message on hitting Gemini rate-limits
• Added graceful quitting when running through the terminal [credit: @momokrono]

I want to thank @momokrono once again for all his help and support—not only in contributing code, but also for extensively helping manage GitHub issues. Thank you, truly—I'll never forget your kind contributions. 💛

Upcoming features:

• Localization (multi-language UI) — @momokrono has built the entire framework for this, and my gratitude is unbounded — this would help so many. It'll be ready by the next release!
• Hotkeys for specific options.
• Support to remove reasoning token markers if needed (PS: DeepSeek R1 & Gemini 2.0 Thinking already work!).
• (researching) Tracked changes/diff check (to compare proofread text with the original).
• Checking that the active window is the same before pasting.
• More feature suggestions on GitHub Issues, and potentially future ones.
• And of course, bug fixes and improvements overall :]

⬆️ Update Instructions:

You can keep using your old config.json to preserve your set-up! Simply bring it over into the new Writing Tools v7.1 folder you'll download below.

🐞 Known Issues

1. On some devices, Writing Tools may not work correctly with the default hotkey.
   To fix it, simply change the hotkey to ctrl+` or ctrl+j and restart Writing Tools.
   PS: If a hotkey is already in use by a program or background process, Writing Tools may not be able to intercept it. The above hotkeys are usually unused.

2. The initial launch of the Writing Tools.exe might take unusually long — this seems to be because AV software extensively scans this new executable before letting it run. Once it launches into the background in RAM, it works instantly as usual.

---

---

---

🆕🎉 Release Notes for the macOS Version by @Aryamirsepasi (v5.0)

• Updated AI providers: New cloud and local AI models (Gemma 3, Gemma 3n, Gemini 2.5, etc.).
• iCloud support for commands.
• Improved default commands. If you are updating from an older version, please reset the default commands in Settings.
• New icon based on the macOS 26 design.
• Numerous bug fixes (Ollama, Intel crash, window resizing, and more).
• The Proofread command now preserves your rich-text formatting.
• New and improved onboarding window.

Please Note:
After updating the macOS version, the tools may sometimes not show up.
To fix this, re-enable accessibility access:

System Settings → Privacy & Security → Accessibility → Select writing-tools → Press the minus (–) button → Press the plus (+) button → Add writing-tools again and enable access.

---

Upcoming Features:

• Text streaming in the response window.
• Better support for reasoning models.
• Context Menu Support

Windows v7.1 | 🆕 macOS v4.2

🎉 Release notes for the Windows version (v7.1):

v7.1 Hotfix Additions:

• Fixed an issue with the OpenAI Provider, and improved & optimised the entire AI Provider architecture.
• Improved the thinking text animation.
• Fixed the default icon arrangement to be the same as v6.

v7 Additions:

1. Customizable buttons! You can now add, edit, remove, and rearrange the buttons.

Huge thanks to @momokrono for building the entire back-end for this 💛! I added the GUI (with draggable buttons, reset to default functionality...).

2. Sleeker pop-up UI

3. A native Ollama AI Provider (using the Ollama API), for easier Ollama setup & custom model-in-memory-time options — entirely thanks to @momokrono!

4. New Gemini model options, with better explanations

5. A new Pause & Resume option to stop Writing Tools from reading your hotkey if necessary. Again, @momokrono so awesomely implemented this :D

5. Other Improvements:

• UX improvements to the Summary etc. pop-up window (optimized initial height)
• Friendlier error message on hitting Gemini rate-limits
• Added graceful quitting when running through the terminal [credit: @momokrono]

I want to thank @momokrono once again for all his help and support—not only in contributing code, but also for extensively helping manage GitHub issues. Thank you, truly—I'll never forget your kind contributions. 💛

Upcoming features:

• Localization (multi-language UI) — @momokrono has built the entire framework for this, and my gratitude is unbounded — this would help so many. It'll be ready by the next release!
• Hotkeys for specific options.
• Support to remove reasoning token markers if needed (PS: DeepSeek R1 & Gemini 2.0 Thinking already work!).
• (researching) Tracked changes/diff check (to compare proofread text with the original).
• Checking that the active window is the same before pasting.
• More feature suggestions on GitHub Issues, and potentially future ones.
• And of course, bug fixes and improvements overall :]

⬆️ Update Instructions:

You can keep using your old config.json to preserve your set-up! Simply bring it over into the new Writing Tools v7.1 folder you'll download below.

🐞 Known Issues

1. On some devices, Writing Tools may not work correctly with the default hotkey.
   To fix it, simply change the hotkey to ctrl+` or ctrl+j and restart Writing Tools.
   PS: If a hotkey is already in use by a program or background process, Writing Tools may not be able to intercept it. The above hotkeys are usually unused.

2. The initial launch of the Writing Tools.exe might take unusually long — this seems to be because AV software extensively scans this new executable before letting it run. Once it launches into the background in RAM, it works instantly as usual.

---

---

---

🆕🎉 Release Notes for the macOS Version by @Aryamirsepasi (v4.2):

• New AI Providers: OpenRouter and Anthropic are now available in the app, and they both support native image recognition thanks to AIProxySwift!
• Fixed Window Size when editing built in commands.

v4.1 Release Notes:

• Revamped Local LLM page: You can now select either an LLM with OCR or a VLM with direct image recognition.
• New Local AI Models: Qwen 3.0 4B, Gemma 2 2B, Qwen2.5 VL
• Fixed Permission Issue: Fixed the annoying bug that plagued previous versions. For future updates you no longer have to reset the permissions after each update. However, if you are using a previous version, you would still have to re-enable accessibility access one last time:

System Settings → Privacy & Security → Accessibility → Select writing-tools → Press the minus (–) button → Press the plus (+) button → Add writing-tools again and enable access.

v4 Release Notes:

• Integrated AIProxySwift for all providers.
• Image Recognition in Finder: Simply open WritingTools on the desired image in Finder, and it will be recognized by the app.
• Image Support for All Providers:
  • Some providers like Google and OpenAI have native image support via their APIs, which is fully utilized here.
  • Others, like Mistral and Local LLM, use OCR and Apple Vision for text recognition on images.
  • For Ollama, you can choose between native support (if your AI model supports it) or OCR via Settings.
• Keyboard Shortcuts for Each Tool:
  You can set up separate shortcuts for each tool in its Edit Page.
  (Note: Shortcuts will only work if the app is running in the background.)
• Font Size Options have been added back to the Response Window.
• New Gemini models, plus a custom option to add your own Google model name for future use.
• UI Improvements & Bug Fixes.
• Spanish Translation added.
  (If you encounter any translation issues in any language, please let me know.)

Please Note:

• From version 5.0 onwards, the app has been renamed to "WritingTools" instead of "writing-tools". When updating from an older version, at first you might find two app icons in the Applications folder. You can, however, remove the older version safely.
• Sometimes after updating the macOS version, the tools may sometimes not show up.
  To fix this, re-enable accessibility access:

System Settings → Privacy & Security → Accessibility → Select writing-tools → Press the minus (–) button → Press the plus (+) button → Add writing-tools again and enable access.

---

Upcoming Features:

• Text streaming in the response window.
• Better support for reasoning models.
• Retain formatting styles after pasting.
• Gemma 3 support as soon as it is completed by the MLX team.
• Support for documents.

Windows v7.1 | 🆕 macOS v4.1

🎉 Release notes for the Windows version (v7.1):

v7.1 Hotfix Additions:

• Fixed an issue with the OpenAI Provider, and improved & optimised the entire AI Provider architecture.
• Improved the thinking text animation.
• Fixed the default icon arrangement to be the same as v6.

v7 Additions:

1. Customizable buttons! You can now add, edit, remove, and rearrange the buttons.

Huge thanks to @momokrono for building the entire back-end for this 💛! I added the GUI (with draggable buttons, reset to default functionality...).

2. Sleeker pop-up UI

3. A native Ollama AI Provider (using the Ollama API), for easier Ollama setup & custom model-in-memory-time options — entirely thanks to @momokrono!

4. New Gemini model options, with better explanations

5. A new Pause & Resume option to stop Writing Tools from reading your hotkey if necessary. Again, @momokrono so awesomely implemented this :D

5. Other Improvements:

• UX improvements to the Summary etc. pop-up window (optimized initial height)
• Friendlier error message on hitting Gemini rate-limits
• Added graceful quitting when running through the terminal [credit: @momokrono]

I want to thank @momokrono once again for all his help and support—not only in contributing code, but also for extensively helping manage GitHub issues. Thank you, truly—I'll never forget your kind contributions. 💛

Upcoming features:

• Localization (multi-language UI) — @momokrono has built the entire framework for this, and my gratitude is unbounded — this would help so many. It'll be ready by the next release!
• Hotkeys for specific options.
• Support to remove reasoning token markers if needed (PS: DeepSeek R1 & Gemini 2.0 Thinking already work!).
• (researching) Tracked changes/diff check (to compare proofread text with the original).
• Checking that the active window is the same before pasting.
• More feature suggestions on GitHub Issues, and potentially future ones.
• And of course, bug fixes and improvements overall :]

⬆️ Update Instructions:

You can keep using your old config.json to preserve your set-up! Simply bring it over into the new Writing Tools v7.1 folder you'll download below.

🐞 Known Issues

1. On some devices, Writing Tools may not work correctly with the default hotkey.
   To fix it, simply change the hotkey to ctrl+` or ctrl+j and restart Writing Tools.
   PS: If a hotkey is already in use by a program or background process, Writing Tools may not be able to intercept it. The above hotkeys are usually unused.

2. The initial launch of the Writing Tools.exe might take unusually long — this seems to be because AV software extensively scans this new executable before letting it run. Once it launches into the background in RAM, it works instantly as usual.

---

---

---

🆕🎉 Release Notes for the macOS Version by @Aryamirsepasi (v4.1):

• Revamped Local LLM page: You can now select either an LLM with OCR or a VLM with direct image recognition.
• New Local AI Models: Qwen 3.0 4B, Gemma 2 2B, Qwen2.5 VL
• Fixed Permission Issue: Fixed the annoying bug that plagued previous versions. For future updates you no longer have to reset the permissions after each update. However, if you are using a previous version, you would still have to re-enable accessibility access one last time:

System Settings → Privacy & Security → Accessibility → Select writing-tools → Press the minus (–) button → Press the plus (+) button → Add writing-tools again and enable access.

v4 Release Notes:

• Integrated AIProxySwift for all providers.
• Image Recognition in Finder: Simply open WritingTools on the desired image in Finder, and it will be recognized by the app.
• Image Support for All Providers:
  • Some providers like Google and OpenAI have native image support via their APIs, which is fully utilized here.
  • Others, like Mistral and Local LLM, use OCR and Apple Vision for text recognition on images.
  • For Ollama, you can choose between native support (if your AI model supports it) or OCR via Settings.
• Keyboard Shortcuts for Each Tool:
  You can set up separate shortcuts for each tool in its Edit Page.
  (Note: Shortcuts will only work if the app is running in the background.)
• Font Size Options have been added back to the Response Window.
• New Gemini models, plus a custom option to add your own Google model name for future use.
• UI Improvements & Bug Fixes.
• Spanish Translation added.
  (If you encounter any translation issues in any language, please let me know.)

Please Note:
After updating the macOS version, the tools may sometimes not show up.
To fix this, re-enable accessibility access:

System Settings → Privacy & Security → Accessibility → Select writing-tools → Press the minus (–) button → Press the plus (+) button → Add writing-tools again and enable access.

---

Upcoming Features:

• Text streaming in the response window.
• Better support for reasoning models.
• Gemma 3 support as soon as it is completed by the MLX team.
• Support for videos and links via Gemini.
• Still testing: evaluating the possibility of using a Core ML or llama.cpp model instead of MLX — which should, theoretically, allow Local LLM to run on Intel Macs as well.

Windows v7.1 | 🆕 macOS v4

🎉 Release notes for the Windows version (v7.1):

v7.1 Hotfix Additions:

• Fixed an issue with the OpenAI Provider, and improved & optimised the entire AI Provider architecture.
• Improved the thinking text animation.
• Fixed the default icon arrangement to be the same as v6.

v7 Additions:

1. Customizable buttons! You can now add, edit, remove, and rearrange the buttons.

Huge thanks to @momokrono for building the entire back-end for this 💛! I added the GUI (with draggable buttons, reset to default functionality...).

2. Sleeker pop-up UI

3. A native Ollama AI Provider (using the Ollama API), for easier Ollama setup & custom model-in-memory-time options — entirely thanks to @momokrono!

4. New Gemini model options, with better explanations

5. A new Pause & Resume option to stop Writing Tools from reading your hotkey if necessary. Again, @momokrono so awesomely implemented this :D

5. Other Improvements:

• UX improvements to the Summary etc. pop-up window (optimized initial height)
• Friendlier error message on hitting Gemini rate-limits
• Added graceful quitting when running through the terminal [credit: @momokrono]

I want to thank @momokrono once again for all his help and support—not only in contributing code, but also for extensively helping manage GitHub issues. Thank you, truly—I'll never forget your kind contributions. 💛

Upcoming features:

• Localization (multi-language UI) — @momokrono has built the entire framework for this, and my gratitude is unbounded — this would help so many. It'll be ready by the next release!
• Hotkeys for specific options.
• Support to remove reasoning token markers if needed (PS: DeepSeek R1 & Gemini 2.0 Thinking already work!).
• (researching) Tracked changes/diff check (to compare proofread text with the original).
• Checking that the active window is the same before pasting.
• More feature suggestions on GitHub Issues, and potentially future ones.
• And of course, bug fixes and improvements overall :]

⬆️ Update Instructions:

You can keep using your old config.json to preserve your set-up! Simply bring it over into the new Writing Tools v7.1 folder you'll download below.

🐞 Known Issues

1. On some devices, Writing Tools may not work correctly with the default hotkey.
   To fix it, simply change the hotkey to ctrl+` or ctrl+j and restart Writing Tools.
   PS: If a hotkey is already in use by a program or background process, Writing Tools may not be able to intercept it. The above hotkeys are usually unused.

2. The initial launch of the Writing Tools.exe might take unusually long — this seems to be because AV software extensively scans this new executable before letting it run. Once it launches into the background in RAM, it works instantly as usual.

---

---

---

🆕🎉 Release Notes for the Native macOS Version by @Aryamirsepasi (v4):

• Integrated AIProxySwift for all providers.
• Image Recognition in Finder: Simply open WritingTools on the desired image in Finder, and it will be recognized by the app.
• Image Support for All Providers:
  • Some providers like Google and OpenAI have native image support via their APIs, which is fully utilized here.
  • Others, like Mistral and Local LLM, use OCR and Apple Vision for text recognition on images.
  • For Ollama, you can choose between native support (if your AI model supports it) or OCR via Settings.
• Keyboard Shortcuts for Each Tool:
  You can set up separate shortcuts for each tool in its Edit Page.
  (Note: Shortcuts will only work if the app is running in the background.)
• Font Size Options have been added back to the Response Window.
• New Gemini models, plus a custom option to add your own Google model name for future use.
• UI Improvements & Bug Fixes.
• Spanish Translation added.
  (If you encounter any translation issues in any language, please let me know.)

Please Note:
After updating the macOS version, the tools may sometimes not show up.
To fix this, re-enable accessibility access:

System Settings → Privacy & Security → Accessibility → Select writing-tools → Press the minus (–) button → Press the plus (+) button → Add writing-tools again and enable access.

---

Upcoming Features:

• Text streaming in the response window.
• Better support for reasoning models.
• Gemma 3 support as soon as it is completed by the MLX team.
• Support for videos and links via Gemini.
• Still testing: evaluating the possibility of using a Core ML or llama.cpp model instead of MLX — which should, theoretically, allow Local LLM to run on Intel Macs as well.

Windows v7.1 | 🆕 macOS v3.1

🎉 Release notes for the Windows version (v7.1):

v7.1 Hotfix Additions:

• Fixed an issue with the OpenAI Provider, and improved & optimised the entire AI Provider architecture.
• Improved the thinking text animation.
• Fixed the default icon arrangement to be the same as v6.

v7 Additions:

1. Customizable buttons! You can now add, edit, remove, and rearrange the buttons.

Huge thanks to @momokrono for building the entire back-end for this 💛! I added the GUI (with draggable buttons, reset to default functionality...).

2. Sleeker pop-up UI

3. A native Ollama AI Provider (using the Ollama API), for easier Ollama setup & custom model-in-memory-time options — entirely thanks to @momokrono!

4. New Gemini model options, with better explanations

5. A new Pause & Resume option to stop Writing Tools from reading your hotkey if necessary. Again, @momokrono so awesomely implemented this :D

5. Other Improvements:

• UX improvements to the Summary etc. pop-up window (optimized initial height)
• Friendlier error message on hitting Gemini rate-limits
• Added graceful quitting when running through the terminal [credit: @momokrono]

I want to thank @momokrono once again for all his help and support—not only in contributing code, but also for extensively helping manage GitHub issues. Thank you, truly—I'll never forget your kind contributions. 💛

Upcoming features:

• Localization (multi-language UI) — @momokrono has built the entire framework for this, and my gratitude is unbounded — this would help so many. It'll be ready by the next release!
• Hotkeys for specific options.
• Support to remove reasoning token markers if needed (PS: DeepSeek R1 & Gemini 2.0 Thinking already work!).
• (researching) Tracked changes/diff check (to compare proofread text with the original).
• Checking that the active window is the same before pasting.
• More feature suggestions on GitHub Issues, and potentially future ones.
• And of course, bug fixes and improvements overall :]

⬆️ Update Instructions:

You can keep using your old config.json to preserve your set-up! Simply bring it over into the new Writing Tools v7.1 folder you'll download below.

🐞 Known Issues

1. On some devices, Writing Tools may not work correctly with the default hotkey.
   To fix it, simply change the hotkey to ctrl+` or ctrl+j and restart Writing Tools.
   PS: If a hotkey is already in use by a program or background process, Writing Tools may not be able to intercept it. The above hotkeys are usually unused.

2. The initial launch of the Writing Tools.exe might take unusually long — this seems to be because AV software extensively scans this new executable before letting it run. Once it launches into the background in RAM, it works instantly as usual.

---

---

---

🆕🎉 Release notes for the native macOS version by @Aryamirsepasi (v3.1):

• Complete new tool management system to fix current issues.
• Added checks to disable Local LLM on Intel Macs. This should prevent the crashes.
• Fix the issue with the themes not updating correctly
• Improved UI
• Bug fixes in Settings, Onboarding and Popup.

Release notes for macOS v3:

• Almost everything new in Windows v7.1.
• Integrated Local LLM (Llama 3.2 3B), the app now can work without any API Keys or Ollama. Please note that the LLM must be downloaded via Settings.
• Support for German and French.
• Ability to close the Popup Window via ESC Key.
• Bug fixes.

Please Note: Sometimes, after updating the macOS version, the tools might not show up. You just have to go to System Settings and give the app accessibility access again. System Settings -> Privacy & Security -> Accessibility -> Select writing-tools and press the minus button -> Press the plus button and add writing-tools again and enable access to it.

Upcoming features:

• Text Streaming in response window.
• Better support for reasoning models.
• Support for Videos and Links via Gemini.
• Image support on all Providers
• Still testing: I am testing and seeing if it is possible to use a Core ML Model instead of MLX. This should theoretically allow Local LLM to run on Intel Macs, too.

🆕 Windows v7.1 | macOS v2

🆕🎉Release notes for the Windows version (v7.1):

v7.1 Hotfix Additions:

• Fixed an issue with the OpenAI Provider, and improved & optimised the entire AI Provider architecture.
• Improved the thinking text animation.
• Fixed the default icon arrangement to be the same as v6.

v7 Additions:

1. Customizable buttons! You can now add, edit, remove, and rearrange the buttons.

Huge thanks to @momokrono for building the entire back-end for this 💛! I added the GUI (with draggable buttons, reset to default functionality...).

2. Sleeker pop-up UI

3. A native Ollama AI Provider (using the Ollama API), for easier Ollama setup & custom model-in-memory-time options — entirely thanks to @momokrono!

4. New Gemini model options, with better explanations

5. A new Pause & Resume option to stop Writing Tools from reading your hotkey if necessary. Again, @momokrono so awesomely implemented this :D

5. Other Improvements:

• UX improvements to the Summary etc. pop-up window (optimized initial height)
• Friendlier error message on hitting Gemini rate-limits
• Added graceful quitting when running through the terminal [credit: @momokrono]

I want to thank @momokrono once again for all his help and support—not only in contributing code, but also for extensively helping manage GitHub issues. Thank you, truly—I'll never forget your kind contributions. 💛

Upcoming features:

• Localization (multi-language UI) — @momokrono has built the entire framework for this, and my gratitude is unbounded — this would help so many. It'll be ready by the next release!
• Hotkeys for specific options.
• Support to remove reasoning token markers if needed (PS: DeepSeek R1 & Gemini 2.0 Thinking already work!).
• (researching) Tracked changes/diff check (to compare proofread text with the original).
• Checking that the active window is the same before pasting.
• More feature suggestions on GitHub Issues, and potentially future ones.
• And of course, bug fixes and improvements overall :]

⬆️ Update Instructions:

You can keep using your old config.json to preserve your set-up! Simply bring it over into the new Writing Tools v7.1 folder you'll download below.

🐞 Known Issues

1. On some devices, Writing Tools may not work correctly with the default hotkey.
   To fix it, simply change the hotkey to ctrl+` or ctrl+j and restart Writing Tools.
   PS: If a hotkey is already in use by a program or background process, Writing Tools may not be able to intercept it. The above hotkeys are usually unused.

2. The initial launch of the Writing Tools.exe might take unusually long — this seems to be because AV software extensively scans this new executable before letting it run. Once it launches into the background in RAM, it works instantly as usual.

---

---

---

Release notes for the native macOS version by @Aryamirsepasi (v2):

• New Feature: Image Processing via Gemini (Thanks to @Joaov41. GitHub: https://github.com/Joaov41)
• Added direct Mistral support
• Added Provider selection in the Onboarding Window
• The installer now has a shortcut to the Applications folder

Note: macOS 14 or later is required to run Writing Tools (due to accessibility API requirements).

Upcoming features:

• Text streaming in the Response Window
• Localisation of the buttons for some languages
• Ability to close the Popup Window via ESC Key
• Ability to work with an embedded local LLM without any configuration

🆕 Windows v7 | macOS v2

🆕🎉Release notes for the Windows version (v7):

You'll love this!

1. Customizable buttons! You can now add, edit, remove, and rearrange the buttons.

HUGE thanks to @momokrono for building the entire back-end for this 💛! I added the GUI (with draggable buttons, reset to default functionality...).

2. Sleeker pop-up UI

3. A native Ollama AI Provider (using the Ollama API), for easier Ollama setup & custom model-in-memory-time options — entirely thanks to @momokrono!

4. New Gemini model options, with better explanations

5. A new Pause & Resume option to stop Writing Tools from reading your hotkey if necessary. Again, @momokrono so awesomely implemented this :D

5. Other Improvements:

• UX improvements to the Summary etc. pop-up window (optimized initial height)
• Friendlier error message on hitting Gemini rate-limits
• Added graceful quitting when running through the terminal [credit: @momokrono]

I want to thank @momokrono once again for all his help and support—not only in contributing code, but also for extensively helping manage GitHub issues. Thank you, truly—I'll never forget your kind contributions. 💛

Upcoming features:

• Localization (multi-language UI) — @momokrono has built the entire framework for this, and my gratitude is unbounded — this would help so many. It'll be ready by the next release!
• Hotkeys for specific options.
• Support to remove reasoning token markers if needed (PS: DeepSeek R1 & Gemini 2.0 Thinking already work!).
• (researching) Tracked changes/diff check (to compare proofread text with the original).
• Checking that the active window is the same before pasting.
• More feature suggestions on GitHub Issues, and potentially future ones.

⬆️ Update Instructions:

You can keep using your old config.json to preserve your set-up! Simply bring it over into the new Writing Tools v7 folder you'll download below.

🐞 Known Issues

1. On some devices, Writing Tools may not work correctly with the default hotkey.
   To fix it, simply change the hotkey to ctrl+` or ctrl+j and restart Writing Tools.
   PS: If a hotkey is already in use by a program or background process, Writing Tools may not be able to intercept it. The above hotkeys are usually unused.

2. The initial launch of the Writing Tools.exe might take unusually long — this seems to be because AV software extensively scans this new executable before letting it run. Once it launches into the background in RAM, it works instantly as usual.

---

---

---

Release notes for the native macOS version by @Aryamirsepasi (v2):

• New Feature: Image Processing via Gemini (Thanks to @Joaov41. GitHub: https://github.com/Joaov41)
• Added direct Mistral support
• Added Provider selection in the Onboarding Window
• The installer now has a shortcut to the Applications folder

Note: macOS 14 or later is required to run Writing Tools (due to accessibility API requirements).

Upcoming features:

• Text streaming in the Response Window
• Localisation of the buttons for some languages
• Ability to close the Popup Window via ESC Key
• Ability to work with an embedded local LLM without any configuration

Windows v6 | 🆕 macOS v2

Release notes for the Windows version (v6):

This is a pretty huge and exciting update :D

1. Improvements to the Summary/Key Points/Table/Chat window — you can now:

• Chat with the summary! You can for more details on particular parts, or ask it to explain things. The chat history is preserved until you close the window.
• Copy the response as markdown.
• I also added a sweet tiny "Thinking..." animation haha.

2. Gemini 2.0 Flash is now the default model. It's more intelligent than GPT 4o and Gemini 1.5 Pro!

3. The Writing Tools Chat Mode (when you invoke Writing Tools without selecting any text) now shows its response in a proper Chat window. So you can now have a quick chat with an LLM with one click, anywhere.

New.Chat.Mode.Demo.mp4

4. There's now an automatic check for updates feature, which checks for a new version by pinging a file in this repo on the initial Writing Tools launch. It'll never annoy you with any pop-up notice or notification — just a small message on the Writing Tools pop-up itself :)

5. Thanks to @ErrorCatDev for significantly improving the About window, making it scrollable and cleaning things up! I've also increased the height (to 720px, the max of a 720p display) to better showcase our awesome contributors :D

6. There's now a Start on Boot toggle in Settings. Thanks to @Vadim-Karpenko for helping implement it!

7. There's now an automatic self-quitting function should Writing Tools ever detect itself malfunctioning (there was a rare bug on waking the PC from sleep that caused Writing Tools to keep spam detecting its hotkey until it was restarted).

8. Misc improvements: Updated dependencies; added an Ollama instructions button to Settings; larger default zoom for the Summary window; some UX improvements.

9. The Settings window has been improved with a scrollbar and smart window height (based on the monitor’s height), solving an issue where it spanned past the border of smaller screens.

10. Slight digression: I added Tips to the README! It has instructions on YouTube summaries & improving compatibility with MS Word.

11. And guess what? Writing Tools is now HALF⚡ its previous size thanks to build optimizations! :D So it'll launch faster and use less RAM.

Upcoming features:

• Editable buttons! (you'll be able to re-arrange buttons, create your own, and edit their prompts).
• More of the feature suggestions in the Issues page.

⬆️ Update Instructions:

Delete your old Writing Tools folder and download the new one (the config file format has changed).

🐞 Known Issues

1. On some devices, Writing Tools may not work correctly with the default hotkey.
   To fix it, simply change the hotkey to ctrl+` or ctrl+j and restart Writing Tools.
   PS: If a hotkey is already in use by a program or background process, Writing Tools may not be able to intercept it. The above hotkeys are usually unused.

2. The initial launch of the Writing Tools.exe might take unusually long — this seems to be because AV software extensively scans this new executable before letting it run. Once it launches into the background in RAM, it works instantly as usual.

---

---

---

🆕🎉 Release notes for the native macOS version by @Aryamirsepasi (v2):

• New Feature: Image Processing via Gemini (Thanks to @Joaov41. GitHub: https://github.com/Joaov41)
• Added direct Mistral support
• Added Provider selection in the Onboarding Window
• The installer now has a shortcut to the Applications folder

Note: macOS 14 or later is required to run Writing Tools (due to accessibility API requirements).

Upcoming features:

• Text streaming in the Response Window
• Localisation of the buttons for some languages
• Ability to close the Popup Window via ESC Key
• Ability to work with an embedded local LLM without any configuration