SLMs & Agent Memory with Cognee & Fastino Labs

Quality of agent memory depends on the quality of extraction. If extraction is slow, costly, or inaccurate, all downstream processes inherit those issues: retrieval, reasoning, recall.Join Fastino Labs and Cognee for an evening on how small, specialised open-weight models can be used in the extraction layer for agent memory.Agenda:Food and drinks will be provided. 😊About Fastino Labs: Fastino Labs is a frontier lab headquartered in Palo Alto, California that develops SOTA SLMs (GLiNER2), fine-tuning tools, and offers optimised inference.About Cognee: Cognee is an open-source AI memory engine that transforms unstructured data into persistent, queryable memory. It enables AI agents to store, retrieve, and reason over information across time and infrastructure, making it possible to build reliable, adaptive, and stateful AI systems that operate seamlessly across cloud and local environments.