Shanghai, Here We Come! On 5/30, OceanBase × LangChain Join Forces to Debut "AgentSeek" and Define a New Paradigm for Enterprise Agent Development
On May 30, OceanBase will team up with the LangChain Community for an offline Meetup themed “Building Highly Reliable, Low-Cost Enterprise Agent Infra.” At the event, AgentSeek — an enterprise-grade agent engineering solution for the Data × AI era — will be fully unveiled for the first time, with a deep dive from the underlying architecture all the way to production practice, decoding the core secrets of scaling AI Agents.

In an era where large models are “blooming everywhere,” the real bottleneck has long since stopped being the models themselves — it lies in how to make agents run efficiently, cheaply, and at scale. Data silos, broken context, missing memory, complex deployment… these “roadblocks” to enterprise AI Agent adoption are about to be cleared one by one.
🕐 Time: May 30
🏠 Location: 35F large conference room, Tower T1 (Moli · Source), Zhangjiang Science Gate, Pudong New Area, Shanghai
❗ Registration note: seats are limited, first come, first served! Scan to reserve now and grab a front-row seat for AI engineering!
Major Launch: the AgentSeek Enterprise Agent Engineering Platform
The core highlight of this event is the launch of OceanBase’s in-house AgentSeek enterprise-grade agent engineering solution.
As OceanBase CEO Yang Bing put it: an agent only cares about getting the task done as efficiently, as fast, and as cheaply as possible — fragmented data is inherently unfriendly to agents, and every act of coordination is a token cost. A system foundation that unifies data and AI represents the direction the data layer is heading.
AgentSeek was built precisely to solve this industry pain point as a unified foundation, with a seven-layer technology stack spanning from data storage to application interaction:
- Unified data foundation (OB4AI): the OceanBase AI-native converged database, capable of unifying relational, vector, document, and graph multi-model data.
- Self-evolving context (SeekContext): a context semantic layer with self-evolution, featuring L0/L1/L2 tiering, traceability, and the ability to evolve.
- Multi-Runtime compatibility: compatible with mainstream runtimes such as LangChain, and through an in-house message gateway and AG-UI protocol layer, it supports multiple application forms including DingTalk, Feishu, and Web UI.
Case Studies Revealed:
- Suanzhi Future: using OceanBase as a unified data foundation, it successfully solved the complex need for efficient hybrid retrieval across vector, scalar, and full-text indexes.
- PPDai: by adopting the OceanBase distributed database, it leverages financial-grade high availability, strong data consistency, and elastic scaling.
Agenda: pure substance, heavy on hands-on practice.
Whether you’re a technical decision-maker, an architect, or a front-line developer, this Meetup will give you a full-stack design methodology for AI Agents from the data layer to the application layer; first-hand, hands-on experience integrating the OceanBase × LangChain ecosystem; and a direct look at the enterprise-grade cases of PPDai and Suanzhi Future, offering insight into the path to scaling Agents.
May 30, Zhangjiang, Shanghai — see you there!