Feature Requests (DISCONTINUED)

Ollama has a new feature fore generating images. I'd like to use this in BoltAI, too. Thanks

In BoltAI 1, attaching a file to a chat showed a token count immediately (before actually sending the message). In BoltAI 2, the token count has ben replaced with a file size (in KB/MB). The token count was much more useful to me so I would know whether or not it would exceed the context window for the model I was using. The file size isn't really relevant (at least to me). Please restore the token count, or make it an option again.

Please add support for a RAG inside projects that we can query inside them. We use another tool for this and it's vital for our workflow to be able to query our knowledge bases without sending the entire file each time.

Feature Request: Enhanced AppleScript Permission Handling for Calendar and Mail Issue Summary When attempting to create a calendar event or access the latest email via AppleScript, the script fails with the error “Not authorized to send Apple events to Calendar” or “Not authorized to send Apple events to Mail,” even after the user has explicitly granted permission in System Preferences → Security & Privacy → Automation. This prevents automation workflows from functioning reliably. Expected Behavior Once the user has granted automation permissions, AppleScript should be able to interact with Calendar and Mail without further prompts or errors. Proposed Solution Implement a service for mail and calendar. Look Spamsieves process…? Thank you for considering this enhancement.

The ability to either speak text or have a system bell as an alarm once a prompt is finished processing. It's mentally freeing if you can just set the prompt off on a multi-minute prompt run and know that you'll get notified once it's finished, and you can just switch back to it

Add Kokoro TTS as a built-in speech engine in Bolt AI 2, alongside OpenAI audio. It enables low-latency, high-quality, local text-to-speech for LLM responses. Motivation Kokoro TTS is fast and lightweight, ideal for real-time responses streaming as LLM outputs tokens. Many users prefer local speech for privacy, offline use, and cost savings, instead of cloud APIs. Making Kokoro a core, selectable backend enhances Bolt AI 2 for multimodal, voice-first workflows. Functionality Kokoro as a backend in audio/TTS settings. Configure model, voice, speed, and response options. Support streaming: send chunks incrementally, start playback early, create real-time speech. Support local process or remote endpoint with URL, API key, request mapping. UI controls: "Play with Kokoro” button, indicating speech status, voice dropdown. Examples Global: set audio provider, endpoint, default voice, speed. Per assistant: enable auto-speak and streaming. Benefits Private local voice for sensitive use. Low-latency, real-time interactions. Cost savings with local compute. Fits power users with local models and self-hosted AI.

When bulleted outlines/summaries are generated in markdown, there's no indentation. This makes it harder to quickly read and navigate when all items are equally aligned. Please add rendering of indentation in markdown bullet points.

We need access to newer models, this should happen automatically without having to update the app. I would like access to new models faster.

By default it seems all floating chat windows are pinned by default (appear on top). I actually think I'd want the default to be unpinned, but I'd be happy with a shortcut. I think this should be separate from the pinning / unpinning of the Quick Prompt window Bonus: I'd like to see my floating windows in my CMD+Tab list of applications / windows.

Since Windows users are more than Mac users, please make a Windows alternative, especially with a plugin that can connect to the terminal so that it can control Windows with AI; it would be very cool for AI to control everything on the computer and also script plugin to even more enchanted connection to Windows PC. I know it's hard, but because of it, you can increase this app's popularity. Thanks.