TypeAgent is sample code that explores an architecture for building a single personal agent with natural language interfaces leveraging current advances in LLM technology. The goal of the TypeAgent team is to explore how to get work done by safely and efficiently combining stochastic systems like language models with traditional software components. Three principles have emerged during this investigation. They are listed below along with examples of how the principles apply to actions, memory, and plans. We are trying to create human-like memory with super-human precision and recall for agent conversations. We are using a new indexing and query processing approach called Structured RAG as the basis for agent memory. To apply agent interfaces to all applications, we need to map user requests to actions at much lower cost and latency than current systems. We have created a system that can distill language models into logical systems that can handle most user requests. Actions and memories flow together. Actions like add to my calendar pickle ball game 2-3pm on Friday yield memories that can become parameters of future actions like put in an hour of recovery time after my pickle ball game. We are working on an architecture, AMP, that enables this natural information flow by integrating actions, memories, and plans. We are applying AMP to the web by creating a browser that enables web sites to register actions through a JavaScript interface. The TypeAgent Shell example is the starting point to explore the single personal agent with natural language interfaces we have built so far. It is an Electron application for interacting with multiple registered agents using a single unified user interface. TypeAgent Shell includes: Single personal agent conversational interface with voice support, collaborate with users to perform and dispatch actions to an extensible set of agents, answer questions, and carry on a conversation, conversational memory based on Structured RAG, integration with TypeAgent Cache to lower cost and latency. Follow these step-by-step instructions to quickly set up tools and environments from scratch to build, run, explore, and deve
