This new release (BrainSoup 1.30.0) is a major update which introduces the following changes:

• Revamped Agent List: The agent list has been revamped to make it clearer and more efficient, especially when dealing with a large number of agents. Agents are now divided into two lists: participants and non-participants, the latter being collapsed when not needed. This change makes it easier to manage your agents and to focus on the most relevant ones.
• Updated the underlying gpt-4o model, which is now abble to output 16384 tokens instead of 4096, allowing for more complex and detailed responses.
• The "Stay active in background" icon has been changed to a robot icon, to better reflect that it is related to automating tasks.
• Updated Doc-E's knowledge to reflect the latest changes in BrainSoup.

This new release (BrainSoup 1.29.0) is a major update which introduces the following changes:

• Source Code Semantic Indexing: BrainSoup can index source code files semantically, allowing your agents to understand your codebase and answer any questions related to it. To do this, simply add your source code to the `Documents` folder or the Sandboxed File System.
• Improved RAG pipeline: Your agents are now much better at leveraging their knowledge to provide accurate and relevant responses.
• GitIgnore: New ability to ignore files and directories listed in '.gitignore' and '.BrainSoupIgnore' files. This feature is particularly useful when working with source code repositories, to prevent irrelevant files from being indexed.
• Better context window management: Adaptative algorithms are now used to get the most out of the available agent's context window.
• System and hidden files, as well as files and directories whose names begin with a dot ('.'), are now hidden to agents and excluded from indexing.
• The `FileSystem` context has been improved to make it able to handle very large file trees more efficiently, whithout consuming too much of the agent's working memory.
• Fixed a bug that reduced the ability of agents to remember past conversations.
• Updated Doc-E's knowledge to reflect the latest changes in BrainSoup.

This new release (BrainSoup 1.28.0) is a major update which introduces the following changes:

• Codestral Mamba!: This is a new model by Mistral has a huge 256K token context window, and is very cost-effective.
• GPT-4o pricing update: We are now using the experimental GPT-4o-2024-08-06 model instead of GPT-4o, which reduces costs by half! According to our tests, the new model is just as performant as the previous one, if not better. But please let us know if you experience any issues.
• Mistral Large pricing update: This powerful model is now 25% cheaper to run.
• Improved multi-agent experience: We've made some improvements to the multi-agent chat orchestration system to make conversations more natural and productive.
• Enhanced vision capabilities: The 'ImageToText', 'Camera', and 'Screenshot' tools are now able to answer very specific questions about the image.
• Optimized Doc-E's settings to improve its performance.
• Fixed a bug that caused BrainSoup to sometimes fail to connect to the Ollama server.
• Fixed a bug that caused the shortcuts to the sandboxed file system to be incorrect when a custom location was used.

This new release (BrainSoup 1.27.1) is a minor update which introduces the following changes:

• A database backup is now created after each successful start, to prevent data loss in worst-case scenarios.
• GPT-4o-Mini is now the default LLM for all new agents.
• Improved the parsing of Markdown lists in the chat.
• Fixed a bug that caused the authentication token not to be refreshed immediately when the computer wakes up.
• Fixed a bug that caused the application to sometimes crash when changing chat room.
• Updated and consolidated Doc-E's knowledge.

This new release (BrainSoup 1.27.0) is a major update which introduces the following changes:

• GPT-4o mini! We've added support for the impressive new model GPT-4o-Mini. This model is smarter than GPT-3.5-Turbo, has a huge 128K token context window (vs 16K for GPT-3.5-Turbo), and is 3 times cheaper to run! We strongly recommend upgrading all your GPT-3.5-based agents to GPT-4o-Mini for massive savings and improved performance.
• Speech to text input! We've added a new feature that lets you speak to your agents by voice. This function is available via a button next to the input field, or via the keyboard shortcut 'Ctrl+S'. It is based on the OpenAI Whisper model, which is highly accurate and takes into account the context of the conversation.
• Mistral Nemo: We've added support for the new open-mistral-nemo model, a very interesting uncensored 12B LLM with a very large context window of 128K tokens, which is smarter than open-mixtral-7B, and only 20% more expensive to run.
• Improved overall cost-effectiveness: We now use GPT-4o-Mini as the base model for all internal orchestration prompts in BrainSoup, resulting in a more robust and cost-effective solution.
• Improved document indexing efficiency: This is a consequence of using GPT-4o-Mini for internal knowledge extraction prompts.
• More reliable WebBrowser tool: We have fixed a problem that sometimes prevented web searches from producing results.
• Better looking login screen.
• Fixed a bug that caused the application to sometimes crash when logging out.

This new release (BrainSoup 1.26.0) is a major update which introduces the following changes:

• New Email Custom Tool: This new tool allows your agents to send emails, with the ability to attach files, add cc/bcc recipients, and more. We have implemented this tool as a Custom Tool written in PowerShell, so you can see how easy it is to create your own tools for BrainSoup. To enable this tool, you just need to set your SMTP server settings in the 'Tools\Custom\Email\config.ps1' file.

This new release (BrainSoup 1.25.2) is a minor update which introduces the following changes:

• Fixed an issue causing some files not to be indexed.
• Fixed an issue preventing some scripting languages from being executed by the Hook manager.
• Updated Doc-E's knowledge about Hooks and how to use them.

This new release (BrainSoup 1.25.1) is a minor update which introduces the following changes:

• Fixed an issue where the application would crash at startup for some users.

This new release (BrainSoup 1.25.0) is a major update which introduces the following changes:

• New FileDownloader tool: This new tool allows your agents to download files from the internet.
• Improved ImageToText tool: The 'ImageToText' tool can now handle online images.
• Improved YouTube tool: Your agent can now also retrieve the title, author, and thumbnail URL of a YouTube video, in addition to the full transcript.
• Improved chat history limit: The pinned messages now never expire even if you set a limit on a chat's history, making sure agents never forget important information.
• Updated Doc-E's knowledge to include the latest changes.
• Fixed a bug causing sevaral file-based tools to stop working since the last release, sorry about that! 😅

This new release (BrainSoup 1.24.0) is a major update which introduces the following changes:

• Hooks! You can now trigger your scripts or programs in response to specific internal events by placing them in the 'Hooks' folder. This powerful feature can be used to update your Custom Contexts, send Custom Events, or interact with external systems.
• More flexible Custom Contexts: In addition to JSON files, you can now define a Custom Context as a tree of small text files. This makes it easier to update specific parts of the context in your scripts without having to generate an entire JSON file. You can now also use small Markdown or CSV documents as Custom Contexts.
• Drive-mapped sandboxed directory: You can now map the active chat room's sandboxed directory to a drive letter for easier access. The mapping is automatically updated when you switch chat rooms.
• Open console in sandboxed directory: We have added a button in the built-in file explorer that allows you to open a console in the sandboxed directory of the active chat room. This can help you run scripts or commands directly in the chat room's environment.
• New TextToImageDallE3 tool: Your agents can now generate high-quality images from text using the latest OpenAI DALL-E 3 model. The TextToImageDallE2 tool is still available as it is cheaper and faster, but the DALL-E 3 model provides better quality images.
• Chat history limits: You can now limit the number of days and messages stored in a given chat room. This is particularly useful for long-running background automation chat rooms to prevent them from consuming too much database space.
• Configurable log level: You can now configure the log level to control the amount of information that is logged. This can help you troubleshoot issues.
• Faster initialization: We have optimized the initialization process by parallelizing asynchronous tasks, making BrainSoup start up faster.
• Updated Doc-E's knowledge to include information about the new features.

This new release (BrainSoup 1.23.0) is a major update which introduces the following changes:

• New GuiAutomator tool: This tool allows your agents to interact with GUI applications. Your agents can now automate tasks in applications that don't have an API. This is a great way to automate repetitive tasks that involve interacting with graphical interfaces.
• New ImageEditor tool: This tool allows your agents to work with images. Your agents can now convert, resize, crop, rotate, flip, and apply filters to images and edit their EXIF metadata.
• New AudioVideoEditor tool: This tool allows your agents to work with audio and video files. Your agents can now convert, trim, merge, add audio or subtitles, extract audio or snapshots, apply effects, and more to audio and video files.
• New Camera tool: This tool allows your agents to see through the camera and answer questions about what they see.
• New Screenshot tool: This tool allows your agents to take screenshots of the screen and answer questions about what they see.
• New GeoCalculator tool: This tool allows your agents to convert between addresses and GPS coordinates and calculate distances between locations.
• New DateTimeCalculator tool: This tool allows your agents do date, calendar and time zone calculations.
• New FileArchiver tool: This tool allows your agents to compress and decompress files and folders in various formats.
• Improved Clock tool: This tool now has more features and takes less agent resources.
• Improved file handling: We have improved the way agents handle files, making all file-based tools more reliable.

This new release (BrainSoup 1.22.0) is a major update which introduces the following changes:

• New CsvRead and XlsxRead tool: Your agents can now extract data from CSV and Excel files using SQL queries, and can even join multiple files to consolidate data from different sources. These tools are very powerful and allow your agents to answer complex questions about your data. This is also a great way to connect your agents to your business data to automate tasks and provide insights.
• New SpeechToText tool: Your agents can now transcribe audio files to text. This uses OpenAI's Whisper model under the hood, and consumes very few credits. Additionally, if the file has already been transcribed during the document indexing process, the tool will not call the AI model, saving credits.
• New ImageToText tool: Your agents can now extract a detailed text description from images. This tool uses OpenAI's GPT-4o model under the hood. If the file has already been processed during the document indexing process, the tool will not call the AI model, saving credits.
• New Mistral models: We have added the open-mixtral-8x22b and codestral models to BrainSoup. open-mixtral-8x22b is very powerful and quite cost-effective, while codestral is specialized in code generation tasks, and very cheap to use.
• Cheaper pricing for Mistral models: We have updated the pricing for Mistral models. mistral-small and mistral-large are now 2 times cheaper!
• Cheaper image processing: We are now using the gpt-4o model instead of gpt-4-vision-preview as the default vision model. This model is twice as cheap, faster and more accurate.
• The 'Can see' and 'Can hear' permissions are now enabled by default for all new agents, as this has no negative impact on performance and usage costs.
• The 'FileSystem' context is now only injected into the agent's working memory if the sandboxed file system is not empty. This will prevent unnecessary context data from being sent to the agents, improving performance and usage costs.
• Optimized Doc-E's settings to improve its performance.
• Fixed a bug causing no information to be added to the message technical details when a tool usage fails. This will make debugging your tools easier.