Moss (YC F25)

Moss adoption is growing 200% MoM 🚀 📈 130+ projects live 📦 300+ indexes created 🏢 50+ companies are actively testing @usemoss 🔥 Strong inbound from voice AI & multimodal agent teams If you are an agent developer, try our product at - usemoss.dev

𝗕𝘂𝗶𝗹𝗱𝗲𝗿𝘀 𝗪𝗵𝗼 𝗦𝗵𝗶𝗽 𝗩𝗼𝗶𝗰𝗲 We're hosting a happy hour for Voice AI builders and founders in SF. Agents, pipelines, real-time infra, if you're deep in the voice stack, this one's for you. No panels. No pitch decks. Just good conversations with people worth knowing. 📍 San Francisco 📅 Friday, March 20 · 5:30 – 8:30 PM → RSVP: luma.com/ha2xhx18 #VoiceAI #AIAgents #VoiceAgents #SFTech

Grab your spot: ordnl.link/Qd5CqcU

𝗦𝗿𝗶(𝗠𝗼𝘀𝘀 𝗖𝗘𝗢) is taking the stage to break down how to build fast, robust voice agent workflows without the latency tax. Join us for an evening of technical deep dives: ⚡ When: March 26 at 5:30 PM PDT 📍 Where: AWS Loft SF (525 Market St) 🛠️ Focus: real-time data, and building resilient Voice-AI architecture. #VoiceAI #AIArchitecture #RealTimeAI #SFTech #AWS

Discord office hours have been a hit. Now we're going IRL. 🏢 Come debug, talk architecture, and meet other builders shipping voice agent products face-to-face with the Moss team. 📍 600 California St 📅 March 19th, 10–11am 🔗 RSVP : ordnl.link/7SCyrMB

Grab the repo here -> git clone github.com/usemoss/moss

Integrating a new AI service shouldn't feel like a research project. We built the Moss repo to fix that. A single, structured collection of drop-in samples to skip the boilerplate and start building Voice AI pipelines with Moss. ✓ Core SDKs: Python & TS flows for querying in sub 10ms, custom embeddings, and metadata filtering ⚡ Real-Time Voice: Pipecat & LiveKit pipelines with sub-10ms audio retrieval Clone it, swap in your code, and go.

Check the docs 👇 ordnl.link/jadSvsP #AIAgents #RAG #SearchEngine

Cleaner context windows = Sharper agent responses. 🧠 Metadata filtering is officially LIVE in Moss! You can now filter your vector search by category, price, or location before hitting your LLM. Available in JS & Python SDKs today.

Quick Start -> ordnl.link/49qqfeC #AI #HealthTech #YC #Developers #HIPAA

Moss is officially HIPAA compliant ✅ Building clinical AI agents usually means wrestling with complex compliance infrastructure. We handled the heavy lifting so you don't have to. Start building for healthcare with the Moss search engine now.

Get Started -> pip install inferedge-moss #Moss #Devtools #Realtime #RealtimeSearch

Hot Reload for dynamic data = Shipped 🚀 Dropping queries to sync is terrible UX. Ignoring mutations = stale context. Moss fixes this by auto-polling & hot-swapping the index directly into memory. Enable now with 1 flag: 𝗺𝗼𝘀𝘀_𝗰𝗹𝗶𝗲𝗻𝘁.𝗹𝗼𝗮𝗱_𝗶𝗻𝗱𝗲𝘅("𝗺𝘆_𝗱𝗮𝘁𝗮", 𝗮𝘂𝘁𝗼_𝗿𝗲𝗳𝗿𝗲𝘀𝗵=𝗧𝗿𝘂𝗲)

Checkout now -> Python: pip install inferedge-moss #VectorSearch #DevTools

Moss is now 935x faster! ⚡️ We just shipped a massive low-level performance overhaul. On a 100k doc query workload: 📉 Latency: 935x faster 📈 Throughput: ~1000x higher Plus: New batch ingestion for effortless 100k+ doc indexing!

We're loving our new Time Square billboard running this week thanks to Brex! 😃 If you happen to see it, let us know!

🚀 inferedge-moss Python SDK v1.0.0b14 is live Now you can run Moss Python SDK on Python 3.14 environment using your custom embeddings.

Try now - moss.dev

Experience the future of agentic search with us! Dive in and see the difference today!

🚀 Exciting News: Introducing Hot Path Cloud Search! We're thrilled to unveil our latest feature designed for speed and reliability. Here's how it makes a difference: