AWS recently introduced a new tool called Multi-Agent Orchestrator that helps developers manage complex AI interactions. The system routes requests to the right AI agent and tracks conversations as they unfold. Developers can get started quickly with pre-built components, or plug in their own custom agents, making it work for everything from simple chatbots to complex AI systems that need to coordinate multiple tasks. The framework handles both streaming and non-streaming responses, and developers can build with either Python or TypeScript. Teams have the option to run everything locally or deploy to the cloud. Microsoft and OpenAI have also recently jumped into the game with their own agent frameworks.
IBM has rolled out version 3.1 of its open-source Granite LLMs, bringing some major improvements under the hood. The new models have been trained on a dataset spanning 12 languages and 116 programming languages, processing 12 trillion tokens in total. The latest version features a redesigned dense architecture that can handle up to 128,000 tokens at once. According to IBM, these Apache 2.0-licensed models excel at tasks like answering questions using external data (RAG), pulling information from unstructured text, and creating document summaries. Developers can now access these models through Hugging Face. IBM first introduced Granite back in May 2024.
