Charlie Mnemonic Update 4: Focus on searching in memories

    SUMMARY:

• Anthropic models
• Search in conversation history and in messages in Long-Term Memory
• Streamlined Email Management
• Enhanced File Handling and User Interface
• Under the Hood Improvements & Looking Ahead

---

We're excited to announce a significant update to Charlie Mnemonic, your trusted open-source AI assistant with Long-Term Memory. This latest release brings improvements that make Charlie more intuitive, efficient, and powerful than ever before, with a focus on enhancing memory search capabilities.

Anthropic models

We’ve added support for Anthropic models such as Claude 3.5 Sonnet and Haiku, allowing seamless switching between OpenAI and Anthropic.

Search in conversation history and in messages in Long-Term Memory

One of the most exciting additions in this update is our advanced chat search functionality. We’ve all been there – scrolling endlessly through conversations, trying to find that one crucial piece of information. Those days are now behind us. Charlie’s new live chat search feature allows you to find specific messages and memories with accuracy. As you type, results appear in real-time, and you can jump directly to the relevant message in the chat tab with a single click. We’ve even implemented query rewriting to improve search results, ensuring you find exactly what you’re looking for, even if your search terms aren’t an exact match.

This feature not only saves time but also provides valuable context, helping you make connections and recall information more effectively.

Streamlined Email Management

Email management has always been a pain point for many, and we’ve taken significant strides to alleviate this. Charlie now offers a more robust email integration system, complete with a draft email list for easier management. Charlie can send emails by their draft IDs, update drafts on the fly, and even process emails in bulk.

We’ve also added a confirmation window for emails (enabled by default) to prevent those heart-stopping moments when you realize Charlie/you have sent an email prematurely. These enhancements, coupled with improved error handling and logging, make managing your inbox through Charlie a breeze.

Enhanced File Handling and User Interface

In today’s digital world, we deal with a multitude of file types, and Charlie is now better equipped to handle them. We’ve expanded support for various image formats, including .jfif, .pjpeg, .pjp, and .ico. The way files are displayed and managed has been overhauled, with separate handling for text and non-text files, and a new popup for text file upload options.

The user interface has received a significant polish as well. From updated CSS styles for file previews and tooltips to improved modal alignments and positioning, every change has been made with user experience in mind. We’ve even updated our error/warning/success message system to provide clearer communication.

Under the Hood Improvements

While many of our changes are visible on the surface, we’ve also made substantial improvements under the hood. We’ve enhanced WebSocket connection handling, implemented better error management, and increased default memory settings for improved performance. 

Looking Ahead

As always, this update is just another step in our ongoing journey to make Charlie the best AI assistant possible. We’re continuously working on new features and improvements, driven by the valuable feedback from our user community.

We invite you to explore these new features and share your thoughts. Join our Discord community to connect with other users and our development team, or follow us on Twitter for the latest updates.

Thank you for being part of the Charlie Mnemonic journey. We can’t wait to see how you’ll use these new features to enhance your productivity and creativity. Here’s to many more exciting updates to come!

Get Involved

The code and data for Charlie Mnemonic are provided under the MIT license, highlighting our dedication to open-source development and community engagement.

We encourage developers and AI enthusiasts to engage with Charlie Mnemonic. If you have insights or developments that could enhance its LTM capabilities, we invite you to contribute. Whether it’s through implementing new features or optimizing existing functionalities, your input is valuable. Please share your contributions by submitting a pull request.

• GoodAI Discord: https://discord.gg/Pfzs7WWJwf
• GoodAI Twitter: https://twitter.com/GoodAIdev

Thank you for reading this blog!

 

Best,
Marek Rosa
CEO, Creative Director, Founder at Keen Software House
CEO, CTO, Founder at GoodAI

Personal bio:

Marek Rosa is the founder and CEO of GoodAI, a general artificial intelligence R&D company, and Keen Software House, an independent game development studio, started in 2010, and best known for its best-seller Space Engineers (over 5 million copies sold). Space Engineers has the 4th largest Workshop on Steam with over 500K mods, ships, stations, worlds, and more!

Marek has been interested in game development and artificial intelligence since childhood. He started his career as a programmer and later transitioned to a leadership role. After the success of Keen Software House titles, Marek was able to fund GoodAI in 2014 with a $10 Million personal investment.

Both companies now have over 100 engineers, researchers, artists, and game developers.

Marek's primary focus includes Space Engineers, the VRAGE3 engine, the AI People game, long-term memory systems (LTM), an LLM-powered personal assistant with LTM named Charlie Mnemonic, and the Groundstation.

GoodAI's mission is to develop AGI - as fast as possible - to help humanity and understand the universe. One of the commercial stepping stones is the "AI People" game, which features LLM-driven AI NPCs. These NPCs are grounded in the game world, interacting dynamically with the game environment and with other NPCs, and they possess long-term memory and developing personalities. GoodAI also works on autonomous agents that can self-improve and solve any task that a human can.