Moss (YC F25)

@usemoss

The retrieval layer for production AI. Sub-10ms search for voice agents, copilots, and real-time AI.

San Francisco, CA

Moss (YC F25)
@usemoss
6h
What if retrieval didn't need to be another network request? Load the index into your application. Query it locally. Get your context back in milliseconds. That's Moss.
00:00
Moss (YC F25)
@usemoss
10h
Your AI shouldn't have to call another server to remember something. Most RAG setups send retrieval requests over a network. When you're building something that needs to respond in real time, that extra trip matters. Here's how Moss handles it ↓
1
Moss (YC F25)
@usemoss
Oct 5
What does AI memory look like at scale? 80,000+ devices. 113M documents every month. 24.8B tokens embedded on device. Aside uses Moss for local embedding, indexing, and retrieval inside its AI browser. Here's how they're building it:
How Aside Powers Persistent AI Memory Across 80,000+ Devices
From moss.dev
1
Moss (YC F25)
@usemoss
Oct 5
New Moss. Closer to the application. Closer to the context. Faster to the answer. moss.dev
00:00
2
Moss (YC F25)
@usemoss
Oct 4
Something is changing at Moss. Tomorrow. 👀
00:00