Every LLM app I've built has the same broken pattern.
Request comes in - reconstruct context from scratch - call LLM - throw context away.
It's wasteful, slow and breaks at scale.
The Problem
Most developers building ai app end up stitching together Redis, vector database and custom middleware just to give their app basic memory.
It's fragile. It doesn't scale. And every team reinvents the same glue code.
What StreamCtx does
StreamCtx is a streaming context database built specifically for LLM applications.
- Streams conversation context in real-time
- Persists session state across requests
- Replaces 3-5 tools with one clean layer
Open Source. MIT/Apache 2.0 Licensed.
solo founder.
Feedback and beta users welcome!
Top comments (0)