AI Launchpad 2026: CocoIndex
CocoIndex fills the gap of context layer for AI where it continuously takes source and transforms it incrementally on source change or logic change to serve live AI agents, at scale.
Co-founder & CTO, CocoIndex
George He, Cofounder & CTO of CocoIndex, was an infra lead at Google and a founding member of the state-of-the-art indexing infrastructure that powers all of Google. He joined with Linghua Jin, previously a tech lead at Google Search and Research. With unique insights from building the largest incremental engine powering the entire web, they set out on the journey of building the incremental engine for Agents. Agents run 50x faster than humans, but the tools they rely on were built for humans. An agent reasoning over a codebase, a conversation graph, a document corpus, or a stream of events needs that data fresh, organized, and cheap to query — not just on the first call, but throughout the long run.

CocoIndex fills the gap of context layer for AI where it continuously takes source and transforms it incrementally on source change or logic change to serve live AI agents, at scale.
The next edition is programmed by practitioners. Tell us what you built and what you learned.
Apply to be a speakerAPPLY TO BE A SPEAKER