正在加载视频...

视频加载失败

StreamDB - a reactive database in a Durable Stream. Designed for AI apps and agentic session state. You give it a Standard Schema. You get type-safe, multiplexed data sync into TANSTACK DB. Links in the 🧵

22,831 次观看 • 7 个月前 •via X (Twitter)

10 条评论

Electric 的头像
Electric7 个月前

Blog post:

Electric 的头像
Electric7 个月前

Agent sessions need state. Tool calls, messages, active generations. User presence, agent registration. In an ideal world you should just be able to declare a schema and have it work.

Electric 的头像
Electric7 个月前

StreamDB does just that -- wrapping a Durable Stream with a Standard Schema to give you typed, reactive agent state.

Electric 的头像
Electric7 个月前

You define your entity types — messages, presence, agents, whatever your session needs — as Standard Schema objects. StreamDB routes events into TanStack DB collections, with end-to-end type-safety.

Electric 的头像
Electric7 个月前

Multiplexing is built in. It's reactive by design. It's durable by design. Everything is multi-user, multi-tab, multi-device and multi-agent out of the box. All reading and writing to the same stream.

Electric 的头像
Electric7 个月前

Read the docs: Check out the demo app:

Electric 的头像
Electric7 个月前

Deploy now on Electric Cloud:

Pedro Filho 的头像
Pedro Filho7 个月前

@tan_stack how no one implemented this together with the cq from @mozilla ( yet?, to make a data sharing layer between agents real time?

Chat Data 的头像
Chat Data7 个月前

@tan_stack Reactive session state is the part a lot of AI apps end up rebuilding badly. Schema first plus type safe sync makes the stack much easier to reason about. Curious how you handle replay and conflict resolution when multiple agents touch the same session state.

jordan 的头像
jordan7 个月前

@tan_stack Whats different from durable state? Also, does this persist the data? I remember there was a large discussion of how persistence will be done in tanstack db. Anyways, very exciting. After trying all of the sync solutions out there, durable-* feels super clean

相关视频