Keynote: Open Models Need Open Memory
summary
Modern AI agents rely on a fast, durable, portable data layer that answers in milliseconds latency, survives restarts, and moves with deployments. The talk claims licensing and governance shape capabilities as much as benchmarks and shows concrete integrations: Light LLM uses Valkey as a semantic cache, Mem Zero uses it as a vector store, and LangChain wires it for RAG retrieval. Valkey is presented as a community-governed Valkey under the Linux Foundation enabling fewer model calls and lower energy use.
AI-written summary · about
related talks
17mKeynote: An OPEN Path to Super Intelligence
33mKeynote: Boring Wins in AI Agents 🔥 Hard-Earned Lessons
59mKeynote: AI without the BS, for humans
30mKeynote: Fireside Chat
13mKeynote: Introductory Remarks
06mKeynote: Cut Database Costs, Fund Innovation with Valkey
35mUsing coding agents with open models
40mOpening Keynote: AI & Platform Teams