Moss

Moss is a high-performance runtime for real-time semantic search built for conversational and multimodal AI. It delivers sub-10ms retrieval so voice agents, copilots, and chat interfaces can retrieve, reason, and respond without waiting, running where the agent lives - in the cloud, in the browser, or on-device. Moss Cloud handles ingestion, embedding, index builds, and distribution through the Moss Control Plane API, while the SDKs (JavaScript, Python, Swift, Elixir, C, and Browser/WASM) load indexes and run queries locally with built-in embedding models, hybrid search, and metadata filtering. Moss is a Y Combinator (F25) company. This profile was enriched from Moss's public developer surface (docs.moss.dev, package registries, and GitHub).

Moss publishes 1 API on the APIs.io network. Tagged areas include Company, Semantic Search, Vector Search, Retrieval, and AI Agents.

Moss’ developer surface includes documentation, API reference, getting-started guide, engineering blog, support, pricing, signup flow, and 22 more developer resources.

🌐 Visit website 📡 Source on GitHub

40.2/100 thin ▬ flat Agent 34/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5

AccessSelf serve

1 APIs 1 MCP Servers

CompanySemantic SearchVector SearchRetrievalAI AgentsVoice AIEmbeddingsRAGDeveloper ToolsOn-Device AI

Kin Score

Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5

Composite quality — 40.2/100 · thin

Contract Quality 0.0 / 25

Developer Ergonomics 16.1 / 20

Commercial Clarity 12.1 / 20

Operational Transparency 2.7 / 13

Governance 0.0 / 12

Discoverability 9.3 / 10

Agent readiness — 34/100 · agent aware

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 15

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 0 / 7

Typed Event Surface 0 / 6

Agent Skills 5 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/moss: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

Moss Control Plane API

REST control plane that powers all index lifecycle operations for Moss. Every action is multiplexed through a single authenticated POST /v1/manage endpoint (initUpload, startBui...

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

SignUp

SignUp

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt

LLMsTxt

MCPServer

MCPServer

AgentSkill

AgentSkill

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Conventions

ErrorCatalog

Lifecycle

DataModel

Components

Conformance

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

Packages

SDKs

CLI

Access & Security 4

Authentication, authorization, and security posture

TrustCenter

Authentication

Compliance

DomainSecurity

Operate 2

Status, limits, changes, and where to get help

Support

Support

ChangeLog

ChangeLog

Commercial 3

Pricing, plans, and the legal terms of use

Pricing

Pricing

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 2

The organization behind the API

Website

Website

Blog

Blog

Source (apis.yml)

aid: moss
name: Moss
description: Moss is a high-performance runtime for real-time semantic search built for conversational and multimodal AI.
  It delivers sub-10ms retrieval so voice agents, copilots, and chat interfaces can retrieve, reason, and respond without
  waiting, running where the agent lives - in the cloud, in the browser, or on-device. Moss Cloud handles ingestion, embedding,
  index builds, and distribution through the Moss Control Plane API, while the SDKs (JavaScript, Python, Swift, Elixir, C,
  and Browser/WASM) load indexes and run queries locally with built-in embedding models, hybrid search, and metadata filtering.
  Moss is a Y Combinator (F25) company. This profile was enriched from Moss's public developer surface (docs.moss.dev, package
  registries, and GitHub).
url: https://raw.githubusercontent.com/api-evangelist/moss/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
x-tier: stub
x-tier-reason: portfolio-lead
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-20'
tags:
- Company
- Semantic Search
- Vector Search
- Retrieval
- AI Agents
- Voice AI
- Embeddings
- RAG
- Developer Tools
- On-Device AI
image: https://www.moss.dev/og-image.png
apis:
- name: Moss Control Plane API
  description: 'REST control plane that powers all index lifecycle operations for Moss. Every action is multiplexed through
    a single authenticated POST /v1/manage endpoint (initUpload, startBuild, getJobStatus, getIndex, listIndexes, deleteIndex,
    getIndexUrl, addDocs, deleteDocs, getDocs), authenticated with an x-project-key header and x-service-version: v1.'
  humanURL: https://docs.moss.dev/docs/api-reference/v1/getting-started/introduction
  baseURL: https://service.usemoss.dev/v1
  properties:
  - type: Authentication
    url: authentication/moss-authentication.yml
  - type: Conventions
    url: conventions/moss-conventions.yml
  - type: ErrorCatalog
    url: errors/moss-error-codes.yml
  - type: DataModel
    url: data-model/moss-data-model.yml
  - type: Lifecycle
    url: lifecycle/moss-lifecycle.yml
common:
- type: TrustCenter
  url: security/moss-trust-center.yml
- type: Website
  url: https://www.moss.dev/
- type: DeveloperPortal
  url: https://portal.usemoss.dev
- type: Documentation
  url: https://docs.moss.dev/docs
- type: APIReference
  url: https://docs.moss.dev/docs/api-reference/v1/getting-started/introduction
- type: GettingStarted
  url: https://docs.moss.dev/docs/start/quickstart
- type: Blog
  url: https://www.moss.dev/blog
- type: GitHubOrganization
  url: https://github.com/usemoss
- type: Support
  url: https://moss.link/discord
- type: Pricing
  url: https://www.moss.dev/pricing
- type: SignUp
  url: https://portal.usemoss.dev/auth/sign-up
- type: TermsOfService
  url: https://docs.moss.dev/docs/tos
- type: PrivacyPolicy
  url: https://docs.moss.dev/docs/privacy
- type: LLMsTxt
  url: llms/moss-llms.txt
- type: Packages
  url: packages/moss-packages.yml
- type: SDKs
  url: packages/moss-packages.yml
- type: CLI
  url: cli/moss-cli.yml
- type: MCPServer
  url: mcp/moss-mcp.yml
- type: ChangeLog
  url: changelog/moss-changelog.yml
- type: Authentication
  url: authentication/moss-authentication.yml
- type: Conventions
  url: conventions/moss-conventions.yml
- type: ErrorCatalog
  url: errors/moss-error-codes.yml
- type: Lifecycle
  url: lifecycle/moss-lifecycle.yml
- type: DataModel
  url: data-model/moss-data-model.yml
- type: Components
  url: components/moss-components.yml
- type: Conformance
  url: conformance/moss-conformance.yml
- type: Compliance
  url: https://trust.moss.dev
- type: DomainSecurity
  url: security/moss-domain-security.yml
- type: AgentSkill
  url: skills/_index.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 18
  pass: local-v1