Moss builds a high-performance runtime for real-time semantic search in conversational AI. Built in Rust and WebAssembly, it delivers sub-10ms lookup times and runs search and embedding inside the application process with no network hop on the hot path, enabling voice agents, copilots, and chat interfaces to retrieve, reason, and respond instantly. Moss offers hybrid retrieval (semantic plus keyword), built-in embeddings, and metadata filtering from a single SDK that runs in browsers, on-device, at the edge, and in the cloud. The company is part of Y Combinator's Fall 2025 batch.
Moss
ActiveReal-time semantic search for Conversational AI
Total raised
$500K
1 round
Stage
Seed
Jan 2025
Team
1-10
since 2025
Pricing
—
Founded
2025
San Francisco, United States
Agent-ready
—
Real-time semantic search runtime for conversational AI
Built in Rust and WebAssembly for high performance
Sub-10ms lookup times
Runs search and embeddings inside the app process with no network hop
No external vector database required
Hybrid retrieval combining semantic and keyword search
Built-in embeddings and metadata filtering
Single SDK runs in browsers, on-device, at the edge, and in the cloud
12/100
Early
MCP server
Public API
Webhooks
OAuth 2.0
SDKs
No public agent surfaces detected yet.
Jan 2025 Seed $500K ● Y Combinator
Capital network
$500K raised ·1 backer·10 network links
- Backers1
- Shared portfoliocompanies these backers also fund
- Extended networkfunds that co-invest alongside them
Vespa.ai
Big-data serving engine for vector and lexical search
AI SearchAI Infrastructure
Perplexity
AI-powered answer engine delivering real-time, cited responses to complex queries.
AI SearchAI Productivity
Parallel
Web search and research API purpose-built for AI agents
AI SearchAI Infrastructure
Profound
AI search visibility platform for Answer Engine Optimization across ChatGPT and Perplexity
AI SearchAI Marketing
Onyx
AI Search
Turbopuffer
Object-storage-native vector and full-text search at massive scale
AI SearchVector Databases
- How fast is Moss?
- Moss delivers sub-10ms lookup times by running search and embeddings inside the application process with no network hop on the hot path.
- Do I need a vector database?
- No. Moss embeds retrieval and embeddings directly in your app, so no separate vector database is required.
- What kind of retrieval does Moss support?
- It offers hybrid retrieval combining semantic and keyword search, plus built-in embeddings and metadata filtering, all from one SDK.
- Where can Moss run?
- The single SDK runs in browsers, on-device, at the edge, and in the cloud, making it suitable for latency-sensitive conversational AI.
Discussion
Sign in to join the discussion.
Sign inExplore more around Moss
Contextual paths to related AI startups, deals and rankings.