Durable Streams
26 posts
@DurableStreams
The data primitive for the agent loop.
Self-modification has been achieved internally
Been building something new, unsure if it's going to be standalone or part of Maple somehow. Introducing Kubly your local desktop Kubernetes companion. See all your clusters, see all deployments, watch realtime pod logs, watch deployments, everything realtime and offline. Build with @tan_stack DB, @ElectricSQL 's durable streams for streaming the Kubernetes state and logs to the UI, and ofc @EffectTS_ for everything in between. Coming very soon
The hardest thing about agents and backends is durability. @workflowsdk fixes this. That LLM you're calling *will* go down. That service *will* rate limit you. That database *will* unexpectedly slow down. You *will* get paged 💀 I've been looking for a unicorn for a decade. I wanted the level of reliability of combining stuff like SQS / Kafka / microservices, and I absolutely did not want *that* at the same time 😂 Truly reliable systems like that are notoriously difficult to reason about, to develop locally, to test, to simulate, to deploy… Workflow SDK solves that without compromises. We're doing what Next.js did for the frontend, but for one of the most important problems of the new generation of backend applications. Notably, Workflow SDK has an incredible self-hosting and multi-cloud story from day 0. We've taken amazing lessons from Next.js and poured them into the many Worlds (adapters) you can deploy to. Congrats to Pranay and the Workflow team on a generational ship: vercel.com/blog/a-new-pro…
Agent sessions shouldn’t be linear. To rewind, explore alternatives, and fan out in parallel, they need a data primitive with branching. Fork is now live for Durable Streams: branch any stream at any point with a single API call. 🔗🧵
Agent sessions shouldn’t be linear. To rewind, explore alternatives, and fan out in parallel, they need a data primitive with branching. Fork is now live for Durable Streams: branch any stream at any point with a single API call. 🔗🧵
It's all about the loop. Agents accumulate state with every step of the loop. This state needs a new data primitive. That's @DurableStreams 🧵👇
We built a collaborative editor with an AI agent as a real-time CRDT peer. It has its own cursor, streams edits into a Yjs rich text document, and resolves conflicts alongside human users automatically. Built with @DurableStreams, Yjs, and @tan_stack AI. 🔗🧵
We built a collaborative editor with an AI agent as a real-time CRDT peer. It has its own cursor, streams edits into a Yjs rich text document, and resolves conflicts alongside human users automatically. Built with @DurableStreams, Yjs, and @tan_stack AI. 🔗🧵
Yjs is the #1 library for collaborative editing on the web. Today we're announcing built-in Yjs support for @DurableStreams. Use it to add multi-user and multi-agent collaboration to your AI apps and agentic systems. Links in the 🧵👇
