Changelog
v1.34.1: Model Context Protocol support
- New: BoltAI is now an MCP client. MCP servers allows you to extend BoltAI's capabilities with custom tools and commands
- New: Added support for GitHub Copilot and Jina DeepSearch
- New: Added OpenAI's new models: o3, o4-mini, GPT-4.1, GPT-4.1 mini, GPT-4.1 nano
- New: Support more UI customization options: App Sidebar & Chat Input UI
- Improved: Automatically pull model list from Google AI
What's new?
Model Context Protocol
The most significant change of this release is MCP support.
An MCP server, short for Model Context Protocol server, is a lightweight program that exposes specific capabilities to AI models via a standardized protocol, enabling AI to interact with external data sources and tools.
MCP servers allows you to extend BoltAI's capabilities with custom tools and commands.
To learn more about using MCP servers in BoltAI, read more at https://boltai.com/docs/plugins/mcp-servers
New AI Providers
BoltAI now supports 2 new AI service providers: GitHub Copilot* and Jina DeepSearch
*Note: an active Copilot subscription is required
OpenAI's new models
This release added support for latest models: o3, o4-mini and GPT-4.1 model family.
Note that to stream o3 model, you will need to verify your org. Alternatively, you can disable streaming for o3 in Settings > Advanced > Feature Flags
More customizations
Go to Settings > Appearance to personalize your app. You can now customize the App Sidebar and Chat Input Box. Enjoy.
See you in the next update π
v1.33.0
- New: Added support for Claude 3.7 Sonnet
- Improved: Added support for reasoning models on OpenRouter
- Improved: Better cache breakpoint handling for Anthropic models
- Other bug fixes and improvements
What's new?
The most notable change in this release is supporting Anthropic's new Claude 3.7 model. This new model allows you to set a custom "thinking budget tokens". You can decide how hard the model think.
BoltAI simplifies this by using the same Reasoning Effort setting:
- Low: 4K thinking tokens
- Medium: 16k thinking tokens
- High: 32k thinking tokens
It's recommended to start with medium (16k tokens) as it's the optimal setting when using Claude 3.7 extended thinking.
v1.32.3 (build 150)
- New: Added support for Github Marketplace, Pico AI Homelab (MLX), Cerebras AI.
- New: Fetch model lists for Custom AI services.
- Improved: o1 models now support streaming.
- Improved: Copy reasoning content to clipboard.
- Improved: Better error handling for AI services.
- Improved: Better Advanced Voice Mode.
v1.32.0 build 146
- New: Added support for OpenAI's
reasoning_effort
parameter - New: Added support for OpenRouter's
reasoning
content. - Fixed: Projects not showing all AI models.
v1.31.0 build 144
- New: Added support for citations when using Perplexity or Web Search AI Plugins.
- New: Show AI Plugin input params if available.
- New: Chats within projects now support drag-and-drop and other operations.
- Fixed: o1 doesn't work with custom GPT parameters.
- Fixed: Cannot setup a new Anthropic service
v1.30.5 (build 143)
- New: Added support for the new DeepSeek Reasoning model.
- New: Thinking UI. Show reasoning content in a popover.
- Improved: Automatically pulls the model list from DeepSeek platform.
- Improved: Automatically loads previous chat messages on second page.
- Fixed: Alt AI Command profile not showing up.
- Fixed: Jumpy scroll experience.
- Fixed: Always enable text selection for user messages.
- Fixed: Floating window feature doesn't work for some users.
- Other bug fixes and improvements.
v1.30.3 (build 141)
- New: Revamped the model selection UI, both in the navigation bar and in the chat settings.
- New: Swipe gestures in chat list. Swipe left to archive & delete, swipe right to star
- New: Supports "true floating" settings for New Chat & New Temporary Chat windows. Find it in Settings β Shortcuts.
- New: Better keyboard shortcuts support. Select next/previous chat with Command+Shift+[ or Command+Shift+]. Select pinned chat with Command+1 to Command+9
- Fixed: o1 model not working (streaming flag must be turned off)
- Fixed: Image sharing showing incorrect model
- Improve scroll performance
v1.30.2 Happy New Year
Happy New Year! This is a big update with many improvements.
- BoltAI Projects: Projects keep chats, files, and custom instructions in one place.
- New: Official support for the DeepSeek platform.
- Better support for Amazon Bedrock: you can set AWS_SESSION_TOKEN, or use your aws credentials profile
- Significant improvement to the sidebar performance and stability.
- Improved search UI: global search bar on the sidebar and local findbar on each chat.
- Improved the Plugin List UI.
- Improved the Chat's System Instruction Configuration UI.
- Improved: You can re-order and bulk delete AI Services now
- Fixed the issue where Gemini 2.0 Flash model cannot use Grounding Tool
- Removed the "Context Length" requirement for Custom Server
- Fixed the issue where BoltAI's sending empty system instruction
- Fixed the issue where O1 models not showing up for some users
- Fixed other crashes related to the sidebar
- Fixed the issue where AI Inline doesn't work with Dvorak QWERTY β layout
- Fixed crashes related to a SwiftUI bug on macOS 12
Read full release note: https://boltai.com/blog/boltai-projects-deepseek-support-and-more
v1.29.4: bug fixes & improvements
This release focuses on bug fixes and other improvements
- Fixed: chat streaming freezes or is very slow
- Fixed:
gpt
inline trigger doesn't work if OpenAI is not the default service - Fixed: AI Command pallete doesn't stay on top
- Fixed: not discovering
beta
updates - Attemp to fix the issue where BoltAI would crash when going back from background
- Fixed the issue where prompt stuck in "continue mode"
v1.29.0: Amazon Bedrock & xAI support, cache breakpoint and more
- Official supports for Amazon Bedrock & xAI
- Set custom cache breakpoint when using Anthropic models
- Convert temporary chat to normal chat
- Added support for o1 models on Azure
- Document Analysis now supports for more file types
- Improved scroll-to-bottom behavior, faster list view
- Improved drag-and-drop experience
- Fixed the issue where control+n / control+p for non-standard keyboard layout
- Fixed the issue where app icon is reverted after update
- Fixed issue where cannot set up Advanced Voice Mode without OpenAI API key
- Fixed issue with Web Search plugin for some Anthropic users
You can read the full release note here: https://boltai.com/blog/amazon-bedrock-and-xai-support-cache-breakpoint-and-more