Moss
Real-time semantic search runtime for AI agents. Sub-10ms semantic, keyword, or hybrid retrieval against project-owned indexes, hosted or on-device. Supports bring-your-own embeddings.
AgentCard object. It is an agent card in spirit rather than in schema — useful for
discovery, but an A2A client cannot assume it will parse.
capabilities-not-objectno-preferredTransportnonstandard-supportedInterfaces
An A2A client finds this agent by fetching the well-known path on the provider's own host. That is what makes an agent card different from every other agent artifact in this catalog: it is provider-published by construction — it cannot be derived, generated, or reconstructed on a provider's behalf.
https://service.usemoss.dev/v1
· transport HTTP
· protocol
non-standard supportedInterfaces
Semantic Search semantic-search
Sub-10ms similarity search against a project index. Tunable alpha blends pure semantic (1.0) and pure keyword/BM25 (0.0) retrieval. Supports top-k, metadata filters, and optional pre-computed query embeddings.
Index Management index-management
Create, load, list, and delete semantic search indexes. Built-in embedding models moss-minilm (fast, default) and moss-mediumlm (higher accuracy), or bring-your-own embeddings per document.
Document Operations document-operations
Add, upsert, retrieve, and delete documents within an index. Documents carry id, text, optional string-keyed metadata for filtering, and optional pre-computed embeddings.
2026-07-28 from https://www.moss.dev/.well-known/agent-card.json,
HTTP 200. The body was saved verbatim and is the sole source for
everything on this page — no field is inferred.
View the captured card.
Providers change what they serve; if this card has moved or changed shape,
the provider profile carries the
current state as of the last build.