Building Open AI Agents: Inference, Memory & Coding Systems
On October 23 in San Francisco, join us for an evening of lightning talks, food, and open discussion as part of Open Source AI Week 2025.
This edition of our community series will focus on making LLMs efficient in practice and designing agents that scale. Expect deep dives into:
Distributed & evolutionary inference: new ways to make large models efficient beyond datacenters
Coding agents in practice: building controllable, IDE-aware agents that actually help developers ship
Agentic memory structures: systems that remember, retrieve, and adapt over time
Real-world deployment: from compiler/runtime optimizations to agents that survive outside of research demos
Over the past year, our events in NYC and SF have brought together 1,500+ developers and researchers, with speakers from Google Labs, Nvidia, Modular, Meta, Snowflake, AI2, Warp, and more.
This time, we’re gathering during Open Source AI Week to keep pushing the frontier of open and practical AI.
📆 Agenda
6:00–6:30pm: Arrival, food & networking
6:30–8:00pm: Lightning talks (20 min each)
8:00–9:00pm: Open discussion & community networking
Whether you’re building infrastructure, fine-tuning models, or experimenting with new agent designs, this is the place to connect with the people shaping the future of AI.