Changelog
v1.22.0 (build 109)
- New: AI Command supports new variable
{clipboard}
, use content from your clipboard - New: Move chat configuration to the right pane
- New: Custom prompt for generating chat title
- New: Added support for
*.tpl
file - Improved: added cost estimates for o1 models
- Improved: filter only
chat
models for TogetherAI - Fixed: cannot use o1 models from GitHub due to
stream
parameter - Fixed: search doesn’t highlight content within code blocks
- Fixed: activate the chat input when typing
/
within a different textview - Fixed: cannot rename archived chats
- Fixed: cannot clone / move inline chats
- Fixed: Anthropic’s
tool_use
error when disabling plugins - Fixed: quotes and other symbols in chat titles
What's New?
This release adds many quality-of-life (QoL) improvements.
1. Move chat configuration to the right pane
The current Popover has an UX issue: it's hard to test the chat paramters. Going back-and-forth between the popover and the chat list is annoying.
I listened to your feedback and move it to the right pane (Inspector Pane). By default, it's collapsed so it won't get in your way.
2. New variable in AI Command
BoltAI now supports a new variable: {clipboard}
. With this, you can choose to prompt on your clipboard content instead of the highlighted text (variable {input}
).
Protip: if you don't use the placeholder {input}
, BoltAI would ignore the highlighted text.
3. Custom prompt for generating chat title
You can customize the prompt for generating chat title now. Go to Settings > General, click the gear button next to the option.
4. Other bug fixes and improvements
I also improved the overall app in this release, especially bugs related to the new macOS Sequoia.
Let me know if it works well for you.
P.S: I'm still working hard on the new iOS app and Cloud Sync. Sign up for early access here: https://app.youform.com/forms/yplbdvx7
Annnnnd that's it for now 👋
v1.21.0 "New Command"
- New: AI Command now supports AI Plugins (only works with the “Open in new window” behavior for now)
- New: A new inline implementation: better compatibility & support cancellation.
- New: Customize how you want the AI Command & AI Inline to work within an app. Go to Settings > Advanced > App Specific Settings.
- Improved: Improve chat list performance (pagination)
- Improved: Added support for custom keyboard layout like Dvorak
- Fixed: OpenRouter integration fails with o1 models
- Fixed: Main Window shows twice on macOS 15
- Fixed: Error related to non-whitespace text with Claude
What's New:
The most notable change in this release is the new implementation for the AI Command feature.
- AI Command now support AI Plugins. Here is a demo video where I use the Instant Command on a video in Finder:
-
New implementation. Previously, BoltAI uses the Accessibility C APIs to get the highlighted text on the active app. In this release, I've switched to a more modern APIs and it should be more robust.
-
More advanced settings. In this release, you can choose how BoltAI reads the highlighted text. Go to Settings > Advanced > App Specific Settings to see the default settings. If you're having troubles with an app, try to use a different strategy.
- Accessibility: BoltAI would use the Accessibility API to fetch the highlighted text. This works best for native apps such as Apple Notes, Xcode or TextEdit...
- Clipboard: BoltAI would emulate Copy event to get the content of the highlighted text. This works best for a web browser or web-based apps such as Discord, Slack, Notion...
- Smart (default): BoltAI checks if the app is web-based or native and would use the proper strategy.
- Other improvements:
- BoltAI supports custom input keyboard layout like Dvorak
- You can cancel the current AI Command or AI Inline request
I've added more than 30 features in the last 3 month. With this release, I'm going to increase the price soon. If you're still on the fence, now is the best time to lock in the current price.
That's it for now 👋
v1.20.5 (build 106)
- New: new import & export UI with more logging
- New: Added support for OpenAI's latest models:
o1-preview
&o1-mini
- Fix: fixed a bug with Data Import & Export
- Fix: fixed an issue with iCloud sync for default plugins
What's new?
This release improves the Data Import & Export feature. You can see the detail logs on the UI and on the Console app.
BoltAI also supports exporting Memory in this version.
v1.20.2
- Improvement: You can focus on the AI Command search box and type content in a different language than English now
- Fixed the issue where some settings are not sync’ed with iCloud
- Fixed the issue where some users have troubles validating license keys
v1.20.0 (build 101)
- New: customize the data folder (documentation)
- New: synchronize some settings with iCloud
- New: export & import encryption key
- New: show Context Length, pricing & sort option for OpenRouter & Together AI models
- New: manage AI Commands, Assistants & Prompts in a new dedicated window
- Improvement: new Window Management implementation for macOS 12
- Improvement: added the Activate Main Window menu option in the menubar icon and Dock Menu
What's New?
1. Locations:
In this release, BoltAI allows you to customize the data folders. With this feature, you can build multiple different "work profiles" and store its data on a different folders on your Mac.
To learn more, refer to the documentation.
2. iCloud sync for some settings:
Building the full Cloud Sync is time consuming. In this version I've added iCloud sync support for some settings:
- Default temperature, context limit, presence penalty, frequency penalty, top P, top K, max tokens
- Default system instruction
I will continue to add support for more settings.
Side note: Please complete this form and help me shape up the Cloud Sync feature. I will send the beta invite to the email you entered here. Much appreciated 🙏
https://app.youform.com/forms/qjqcrcub
3. Dedicated windows for AI Commands, Assistants & Prompts:
Managing these data within the Settings window can be inconvenience. From this release, you can open the dedicated window in the menu item Window > Manage Command
Alternatively, you can also find it in the gear ⚙️ icon button in the sidebar.
4. View context length, pricing & sort data for OpenRouter & TogetherAI models.
OpenRouter & TogetherAI provide a lot of models for you to use. This can be overwhelming.
You can easily view the context length & pricing in this version. Go to Settings > Models > OpenRouter > Models.
Data is pulled directly from their API.
And that's it for now 👋
v1.19.1 (build 100)
BoltAI just reached its 100th iteration 🎉
- New: Import data from Claude.ai, including attached documents (Read guide)
- Improved: Automatically fetch TogetherAI model list
- Improved: Estimate costs when using TogetherAI models
- Improved: Enable plugin selection for custom AI server. Note: make sure your custom API endpoint support the
tools
andtool_use
parameters. - Fixed: Cannot use
gpt-4o-mini
as the default model for Image Analysis - Fixed: Main window not re-open when clicking on the dock icon (macOS 12)
- Fixed: Message Editor on dark mode doesn't look good (macOS 12)
v1.19.0 (build 99)
- New: Sync documents with the file system. Go to Chat Configuration > Project
- Improved: Auto focus on the text editor when editing chat messages
- Improved: Remember text editor preview pane setting
- Improved: Remove the start/stop sounds when using Inline Whisper
- Improved: Optimize file reading performance
- Fixed: Memories Included When Plugin Switched Off (#153)
What's new
The most notable change of this release is the new "File Sync" feature. By default, when attaching a document, BoltAI parses the content of the file and stores it in the local database.
This approach has a few advantages:
- BoltAI continues to work even if the file is deleted
- There will be no "surprise bill" when you accidentally add a lot of content to the file
- Take advantage of the Prompt Caching capability to reduce cost
However, it has a major drawback: the file content is not always up-to-date.
Starting v1.19.0
, you can enable the File Sync feature (see screenshot). You can turn it on by default in Settings > General.
This is espeically useful when you're working with source code.
Until next time ✌️
v1.18.4 (build 98)
- New: View Document's Ingested Content.Go to Chat Configuration > Project to use it.
- Improved: Handle stop reason
max_tokens
for Claude (show Continue button) - Improved: Added 16k and 32k
max_tokens
configuration options - Improved: Show correct error message when Claude server is overloaded
- Fixed: Use multiple beta headers for Anthropic Claude
- Fixed #146: Invisible text in "Edit Message" window when editing prompts
v1.18.2 (build 96)
- New: Added OpenAI's latest model ChatGPT-4o
- Improved: Added the "Scroll to bottom" button
v1.18.1 (build 95)
- New: Preview Code. Open generated HTML code with your default web browser.
- New: Added images analysis support for Gemini models