Moss
Semantic search runtime for AI agents that indexes documents and answers queries inside the agent's own process, in the browser, on edge runtimes, on devices or in the cloud, with Python and TypeScript SDKs and an MCP server; free developer plan, then $30 and $200 monthly plans plus usage costs.
What it does
- Vector search
- Knowledge retrieval
Features 4
- In-process retrievalRuns retrieval inside the same process as the agent so no network hop is needed.
- Runs where the agent runsWebAssembly build for browser, mobile, desktop, edge and cloud runtimes.
- Replaces the vector databaseCovers retrieval workloads on the critical path without a separate vector store.
- LLM framework integrationsWorks with LangChain and the Vercel AI SDK.
Sources
- Pricing
-
Pricing page: Developer $0 a month plus usage costs with $5 monthly free credits; Hobbyist $30; Start-Up $200; Enterprise custom; pay-as-you-go storage, ingest, egress and session-minute rates.
- Description
-
Official documentation · 18 Oct 2026
Home page: "Get <10 ms search with no vector databases and no latency bottlenecks. Runs directly in browser, edge, device, or cloud."
- What it does
-
Official documentation · 18 Oct 2026
Home page: "Get <10 ms search with no vector databases and no latency bottlenecks. Runs directly in browser, edge, device, or cloud."
- Sold within
-
Self-serve start with a free Developer plan and published Hobbyist and Start-Up plans; Enterprise by demo.
- Name
-
Official documentation · 18 Oct 2026
Name as published on the product page.
- URL
-
Official documentation · 18 Oct 2026
Product page, read 2026-10-18.
- Deployment
-
Official documentation · 18 Oct 2026
Home page FAQ: "Moss compiles to WebAssembly and can run in the browser, on mobile and desktop devices, on edge runtimes, or in the cloud."
- Interfaces
-
Official documentation · 18 Oct 2026
Home page: Python and TypeScript code samples, an MCP Server integration and a Moss Portal sign-in.
Something wrong here? Send a correction — quote this product id: moss-semantic-search.