Jeremy Adams demonstrates a personal agent built on a Raspberry Pi 4BA personal AI agent uses a person's authorized goals, preferences, routines, context, and tools to provide continuing individualized assistance. using NanoClaw and Docker. He describes using WhatsApp to communicate with the agent and cloud-hosted models for inferenceInference is the use of a trained model to produce an output from supplied input..
He connects the agent to Neo4j, first querying a movie graph and then exploring a graph-based memoryAI agent memory is stored information that an agent can retrieve and use across steps, sessions, or changing contexts. of people, places and eventsA knowledge graph represents entities and their relationships in a structured form that can be queried and connected..
A microphone and local voice transcriptionAutomatic speech recognition converts spoken language into text or structured linguistic output using signal processing and machine learning. let him collect notes from conference exhibitors, including in an offline workflow. He shows how he later enriches the data in a graph and explores shared themes.
Watch on YouTube
