In Review

In Progress

Completed

Main Roadmap

Hey Daniel,I was thinking about what we should tackle next, and I had a pretty cool idea. You know that Google NotebookLM app, where you can basically upload your PDFs and "talk" to them? We should seriously consider add this as part of BoltAI.Why this is necessary:<ul><li>No More Guesswork: The AI stops "making things up" (hallucinating) because it's tied directly to the user's own truth.</li><li>The Ultimate Personal Assistant: BoltAI becomes a personal expert, a research assistant, and a project manager all in one. It turns a "cool" AI tool into an "can't-live-without-it" part of their workflow.</li></ul>What do you think? CheersMax

RAG feature  / NotebookLM clone within BoltAI

unmatchedintel

Hi! I would love to have a Canvas like feature where for example emails are written or to separate the code from the chat. Thanks!

Canvas like feature

Pablo

Is it possible to link multiple Agents together in a single workflow?{{input}} → {{Agent 1}} → {{Agent 1 output}} → {{Agent 2}} → {{Returned output}}

Multi-Step Agent Workflows

Dave of the North

Like other tools of the same style (keyring for example), could Boltai in the future be able to interact with the content of a web page present in a web browser? I know you can copy the url and provide it to Boltai, but it's less convenient than being on a page, launching the Boltai shortcut and working with the page content.

interaction with browser windows

freeshare

In this new version, the toolbar no longer shows the chats in the projects. I need to click on the project and access the chats from the project’s dashboard. This is very unhandy and a step backwards in usability compared to V1. I hope it can be solved soon.

Make chats inside projects visible  in toolbar

paulusnp

Show conversation cost like in v1

tiyare

I'm curious about the new implementation for MCP servers. I would like to test both the Obsidian MCP and the one for Logseq as well. They require manual insertion. Is there a JSON configuration available like in version 1?

Plugins are missing custom MCP addition

Nick Cent

Like the title says it would be great to be able to use the BoltAi Mac export for iOS in the absence of a sync functionality

Import Mac BoltAi data to iOS for easy setup

User

Chat summaries currently do not work (I guess, fine for Beta). But I was thinking - how cool would it be to be able to edit auto-summary prompt? This would allow me to: - mark specific topics for easier navigation (i.e. prompt to add [TAG] in front of chat name by topic), - follow certain naming conventions (then I can export multiple chats for further use and won’t need to rename them).

Editable prompt for chat summaries (titles)

Andrey

To access my server I need to put in the header a bearer token. I don't see that option. Thanks

Authorization for Remote MCP Server

Michael Horwitz

It’s important for the user to monitor and track their AI generation costs, and it should be greater if it can estimate cost of the next generation It should have 1. Tokens usage for each generation (input/output and thinking tokens) 2. Current context window usage, such as tokens of current input, total tokens of all previous messages, system-prompt, MCP and Toolings And it would be awesome if it had a dashboard for generation logs.

AI tokens usage monitoring and estimation

Planxnx

As a user of the Bolt v2 app, I am getting an error when I try to continue a conversation. The error message is: "Invalid prompt: The messages must be a ModelMessage[]. If you have passed a UIMessage[], you can use convertToModelMessages to convert them." This prevents me from continuing my conversations in the app.

Error in Bolt v2 App: "Invalid prompt" when continuing a conversation

Purple Rainbow

It seems like reasoning is not viewable until after the response is complete. I would like the ability to view the reasoning as it streams, especially for slower local models.

Streaming Reasoning Output

Potatoh Salade

I want to be able to "star" or favorite specific AI models in the model selection list (especially for providers like OpenRouter with 100+ models) so that they are pinned or surfaced to the top for quick access. This is similar to the design pattern used in the Cline VS Code extension. It is very annoying to scroll through a huge list to find frequently used models.

Favorite/Star models to pin them to the top of the selection list

Aquamarine Savanna

Hi Denial,I’m having a critical issue with importing chats.1- I imported chats to BoltAI v1 from ChatGPT (conversations.json)✅ All chats imported correctly 2- I imported chats to BoltAI v2 from BoltAI v1 (conversations.json)❌ Incorrect chats context❌ Missing responses❌ Incorrect timeline within the conversation This is a screenshot after importing to BoltAI v2 from BoltAI v1 <img data-width="100%" data-align="left" alt="" data-featurebase-content-key="646b16f66b8d963816ca5dc7/post/693850a02296290466196e8b/019b03ee-3494-70b8-a383-1473fcc7c5c2/b64u-Q2xlYW5TaG90IDIwMjUtMTItMDkgYXQgMTguNTYuNTBAMngucG5n.png" src="https://646b16f66b8d963816ca5dc7.featurebase-attachments.com/c/post/693850a02296290466196e8b/019b03ee-3494-70b8-a383-1473fcc7c5c2/b64u-Q2xlYW5TaG90IDIwMjUtMTItMDkgYXQgMTguNTYuNTBAMngucG5n.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260204T220000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260204%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=f8507a2e9086a7b6fa9bb1da924c9f30e8729ced166614da25a559a740cdfc55" data-featurebase-content-filename="CleanShot 2025-12-09 at 18.56.50@2x.png">Here is the issue (BoltAI v2 on the left - BoltAI v1 on the right)<img data-width="100%" data-align="left" alt="" data-featurebase-content-key="646b16f66b8d963816ca5dc7/post/693850a02296290466196e8b/019b03f6-08f0-7f62-952e-1ae8ba068eba/b64u-U2NyZWVuc2hvdCAyMDI1LTEyLTA5IGF0IDcuMTcuNTbigK9QTS5wbmc.png" src="https://646b16f66b8d963816ca5dc7.featurebase-attachments.com/c/post/693850a02296290466196e8b/019b03f6-08f0-7f62-952e-1ae8ba068eba/b64u-U2NyZWVuc2hvdCAyMDI1LTEyLTA5IGF0IDcuMTcuNTbigK9QTS5wbmc.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260204T220000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260204%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=085acba740725401935cef2c1c80827b98f94d6aadeba152da2154d4ec7d7aea" data-featurebase-content-filename="Screenshot 2025-12-09 at 7.17.56 PM.png">Notes:<ul><li>This issue not for certin chats. 90% of the 302 chats importaed have the same issue.</li><li>I redid the importing again, same issue.</li><li>I exported the conversation from ChatGPT again, same issue</li></ul>Rakan

Import Chats from BoltAI v1 Issue

Rakan Alkhnaini

Overview: The application fails to establish a connection with the Azure OpenAI API when using Bolt v2, resulting in a "Connection failed" error. The exact same credentials (Endpoint, API Key, Deployment Name) work successfully in Bolt v1.Environment Metrics:<ul><li>Model: GPT-4o mini (Azure)</li><li>Success Version: Bolt v1 (Confirmed working in Screenshot 1)</li><li>Failure Version: Bolt v2 (Connection failed in Screenshot 2)</li><li>Error Message: "Connection failed. The request could not be completed (no response was received). Please try again."</li></ul>Suspected Technical Causes for Investigation:<ol><li>Request Header construction: Azure OpenAI requires specific headers (<code>api-key</code>). Bolt v2 might be misformatting the header or incorrectly nested the <code>api-key</code> within the Bearer token field, which Azure doesn't always support depending on the SDK implementation.</li><li>Endpoint URL Formatting: Bolt v2 might be appending <code>/chat/completions</code> or <code>/openai/deployments/...</code> differently than v1. If the base URL in the config includes the deployment path, v2 might be double-concatenating it, leading to a 404/Connection refused error.</li><li>CORS or Proxy Issues: If Bolt v2 introduced a new backend architecture or server-side proxy, the request might be failing pre-flight or being blocked by the Azure networking firewall (reaching a "no response" state).</li></ol>Recommended Debugging Steps:<ul><li>Compare the JSON payload structure between v1 and v2; Azure is strict about the <code>messages</code> array format and doesn't support certain parameters that standard OpenAI does.</li><li>Verify if the Model Deployment Name is being passed correctly in the URL path for v2.</li></ul><div data-type="horizontalRule"><hr></div>Summary for the Developer:Since it works in v1 but not v2 with identical settings, this is likely a change in how Bolt v2 constructs the fetch request to the Azure-specific endpoint.<img data-width="100%" data-align="left" alt="" data-featurebase-content-key="646b16f66b8d963816ca5dc7/post/696602e4285661c372dcd82d/019bb67b-3500-7bed-9635-dce6839de388/b64u-Mi5wbmc.png" data-featurebase-content-filename="2.png" src="https://646b16f66b8d963816ca5dc7.featurebase-attachments.com/c/post/696602e4285661c372dcd82d/019bb67b-3500-7bed-9635-dce6839de388/b64u-Mi5wbmc.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260204T220000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260204%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=1e4a441d13eed26c87690dbec463554e7b45b769e85987eeea47cdc1db3b21b4"><img data-width="100%" data-align="left" alt="" data-featurebase-content-key="646b16f66b8d963816ca5dc7/post/696602e4285661c372dcd82d/019bb67b-2598-79bd-addd-6ce67fccb468/b64u-MS5wbmc.png" data-featurebase-content-filename="1.png" src="https://646b16f66b8d963816ca5dc7.featurebase-attachments.com/c/post/696602e4285661c372dcd82d/019bb67b-2598-79bd-addd-6ce67fccb468/b64u-MS5wbmc.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260204T220000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260204%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=94b17e4bd23d5068264d402872cf4447f4237d5b37d956da6d7a20ea8ec63ae4">

Azure OpenAI Connection Failure in Bolt v2

IbrahimMan

The error is: <code>messages.1: 'text_editor_code_execution' tool use with id 'srvtoolu_x&lt;snip&gt;’ was found without a corresponding ‘text_editor_code_execution_tool_result’ block</code>

Trying to resume interrupted conversation with Calude code execution block

dragonflyred

Set up encryption key in BoltAI desktop. Then tried to use mobile app - but ended up in a loop that never ends.Video:<a target="_blank" rel="noopener noreferrer nofollow" class="link" href="https://www.dropbox.com/scl/fi/pobybtzktz77lcbix95hk/ScreenRecording_11-03-2025-23-52-22_1.MP4?rlkey=ks4mfiwi4bb6ubcqhlurcy1lu&amp;st=3zt8390z&amp;dl=0">https://www.dropbox.com/scl/fi/pobybtzktz77lcbix95hk/ScreenRecording_11-03-2025-23-52-22_1.MP4?rlkey=ks4mfiwi4bb6ubcqhlurcy1lu&amp;st=3zt8390z&amp;dl=0</a>

Infinite API decryption

Hi,I’ve added the <a target="" rel="noopener noreferrer nofollow" class="link" href="https://github.com/54yyyu/zotero-mcp">zotero-mcp</a> server to BoltAI.Using ChatGPT with the API works fine, it sees the server. But for some reason the exact same model, when connected via my Codex account, can’t see the server. Is this a bug?Thank you!Device: macOS 26.2Version: 2.6.1 build 51

MCP server don’t seem to work with Codex?

Alexandre Champagne-Ruel

Regarding the settings: Agents and Workflows have a “bulk edit” button that allows for mass-delete. Please add an equivalent function for the “AI Services” pane. Otherwise deleting 40+ models is not feasible. <img data-width="100%" data-align="left" alt="" data-featurebase-content-key="646b16f66b8d963816ca5dc7/post/6966abbdc294ac9c398c5178/019bb90b-ecb5-70d9-a3de-f54dbd2fb609/b64u-aW1hZ2UucG5n.png" src="https://646b16f66b8d963816ca5dc7.featurebase-attachments.com/c/post/6966abbdc294ac9c398c5178/019bb90b-ecb5-70d9-a3de-f54dbd2fb609/b64u-aW1hZ2UucG5n.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260204T220000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260204%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=69a234c0bdcf331578234f66126963970ee3cca36d850f2f0e5a287f6a3b7435" data-featurebase-content-filename="image.png">

Please add *bulk edit* for “AI Services” settings

Jens Nestel

The app currently only allows uploading files with sizes &lt;25MB, which is not enough. My pdf files are larger than this limit.

Remove file size restrictions

Chung Ling Lai

It is SUPER annoying to have to re-enable plugins for every new chat. You used to be able to set defaults so it would, for example, do web fetch and web search w/o having to open up the plugins list and enable every single time.

Allow setting default plugins (you could do this in v1!)

I integrated v0 model via api, mow the model switcher in the chat screen broke and is not letting me switch to another model, making the app unusable.

Integrating a custom llm breaks model switcher

kamili.kamil

I'm having an issue. I am trying to set up my custom provider in iOS using the exact same settings that I use on my Mac desktop, but it's not working. The same settings, the same base URL, and the API key work perfectly on my Mac desktop. I think there might be some sort of error. If you could help me fix this, it would be amazing because I love using the custom provider on my Mac, and I would really like to use it on iOS as well. The error I get when I try to “Fetch Models”. <img data-width="100%" data-align="left" data-featurebase-content-key="646b16f66b8d963816ca5dc7/post/67ed9c4b52e3254f3355102d/0195f82a-3ad2-7152-a031-cf66c55f64d6/b64u-aW1hZ2UucG5n.png" src="https://646b16f66b8d963816ca5dc7.featurebase-attachments.com/c/post/67ed9c4b52e3254f3355102d/0195f82a-3ad2-7152-a031-cf66c55f64d6/b64u-aW1hZ2UucG5n.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260204T220000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260204%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=9264d46b32bf8f3fbf4afff7f80cfe1b247ca767844b701c322a111eb9906dfe" data-featurebase-content-filename="image.png">

Custom Provider in iOS not working (working on MAC though)

adithyan.i4internet

V1 has indentation, v2 has no indent. Unusable for structured output. I hope there’s better indent on V2 than V1.V1 also still has uneven indentation. You should make it more precise, next bullet should start by inherits previous bullet starting point and so on. <img data-width="100%" data-align="left" alt="" data-featurebase-content-key="646b16f66b8d963816ca5dc7/post/69468afdc7eaef6214511ebe/019b3b8b-a517-744d-9df3-2a7bafc27878/b64u-VGFuZ2thcGFuIExheWFyIDIwMjUtMTItMjAgcHVrdWwgMTguMzEuMzUucG5n.png" data-featurebase-content-filename="Tangkapan Layar 2025-12-20 pukul 18.31.35.png" src="https://646b16f66b8d963816ca5dc7.featurebase-attachments.com/c/post/69468afdc7eaef6214511ebe/019b3b8b-a517-744d-9df3-2a7bafc27878/b64u-VGFuZ2thcGFuIExheWFyIDIwMjUtMTItMjAgcHVrdWwgMTguMzEuMzUucG5n.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260204T220000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260204%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=f7437e1efe5c277cbc9317bbc7f87f5eddbd0fed88387b2ae3c7c44919a55a65"><img data-width="100%" data-align="left" alt="" data-featurebase-content-key="646b16f66b8d963816ca5dc7/post/69468afdc7eaef6214511ebe/019b3b8b-f0fb-7bec-a6a3-888b182740cf/b64u-VGFuZ2thcGFuIExheWFyIDIwMjUtMTItMjAgcHVrdWwgMTguMzIuNDcucG5n.png" data-featurebase-content-filename="Tangkapan Layar 2025-12-20 pukul 18.32.47.png" src="https://646b16f66b8d963816ca5dc7.featurebase-attachments.com/c/post/69468afdc7eaef6214511ebe/019b3b8b-f0fb-7bec-a6a3-888b182740cf/b64u-VGFuZ2thcGFuIExheWFyIDIwMjUtMTItMjAgcHVrdWwgMTguMzIuNDcucG5n.png?X-Amz-Expires=3600&amp;X-Amz-Date=20260204T220000Z&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Credential=DO801TYC4FCVNNEKURKM%2F20260204%2Ffra1%2Fs3%2Faws4_request&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Signature=2771201d4f77e4ecaaa84b30ae2639341b6605f5624cb0730bf6043d895ffa0b">

Bad Indentation

Adam Ram

See attached video.<video data-width="100%" data-align="left" alt="" data-featurebase-content-filename="78627619277__5224E38B-CBCE-4C97-BCB3-AC0CF51CEA11.MOV" data-featurebase-content-key="eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJvYmplY3RLZXkiOiIwMTlhZDk1ZC1mMTlkLTdjOTgtYjMwMi1mYWQwNTgxNTlmYmMiLCJ0eXBlIjoidmlkZW8tdXJsIiwicmVzb3VyY2VJZCI6IjY5MmQ2N2Y1ZjhjMTIxMzk4YzExZDc1MCIsInJlc291cmNlVHlwZSI6InBvc3QiLCJvcmdJZCI6IjY0NmIxNmY2NmI4ZDk2MzgxNmNhNWRjNyIsImlhdCI6MTc2NDU4MzQxM30.zXjJulX9wG5zlyp1ronjgc1NI3qe_KKUJoIlsmrJoI8" src="https://646b16f66b8d963816ca5dc7.featurebase-attachments.com/c/videos/eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJvYmplY3RLZXkiOiIwMTlhZDk1ZC1mMTlkLTdjOTgtYjMwMi1mYWQwNTgxNTlmYmMiLCJleHAiOjE3NzAyNDYwMDAsInR5cGUiOiJ2aWRlby11cmwiLCJvcmdJZCI6IjY0NmIxNmY2NmI4ZDk2MzgxNmNhNWRjNyIsInJlc291cmNlSWQiOiI2OTJkNjdmNWY4YzEyMTM5OGMxMWQ3NTAiLCJyZXNvdXJjZVR5cGUiOiJwb3N0In0.UfmDoc-FF9_H5Y7gSAMM28aIlTwbiLUvrJFUEbrRt5g/manifest.mpd"></video>

Unable to switch on Tools

Efrain Salas

When attempting to copy the output of a response in the instant chat window, the value stored in the clipboard is blank or null - meaning it also replaces whatever was stored in the clipboard originally. This occurs if I use either icon underneath the message, or if I click the three dots and select “Copy Message to Clipboard”.For what it is worth, I can manually select the output and use cmd-c to copy the text.

Copy Message to Clipboard Doesn't Work in Instant Chat

jbakerr

Hi Daniel,Many remote MCPs (such as Atlassian, Linear, etc.) require authentication. Currently, there isn't a way to pass authentication credentials, which limits our ability to connect to and leverage these servers. The MCP functionality should support the OAuth flow or passing Auth credentials as Bearer Token. Adding support for authentication would be an incredibly valuable enhancement, unlocking the full potential of these integrations.Thank you for considering this, and best regards, Max

Feature Request: Support OAuth Flow and/or Bearer authentication for remote map

Maximilian Christl

I wear glasses and really miss the font size controls. I know you had this feature before and will add it back—can't wait!

Font Size adjustment

I love the new Instant Chat feature! Once I type in a query, it would be helpful to resize the window. My use case is when I query something, the text gets long and I have to scroll through it. This makes reading long summaries and code in the instant chat window.