Memories

Memories.ai (MAVI) is a video-intelligence platform that turns raw video into searchable, agent-ready understanding. It ships three products on a shared video-understanding stack: Visual Intelligence (stateless REST APIs for transcription, captioning, frame description, embeddings, social-media scraping, and real-time audio/video stream moderation via VLMs such as Gemini, Nova, and Qwen), Visual Search (an auto-indexed private and public video/image library searchable by text, image, or transcript), and Visual Agents (pre-built workflows for video search, AI video editing, and screenplay extraction). The platform authenticates with sk-mavi- API keys, bills on a unified per-endpoint credit model, and is HIPAA, SOC 2 Type 2, and GDPR compliant. It is a Seedcamp portfolio company.

Memories publishes 3 APIs on the APIs.io network: Serve API, Stream Understanding API, and Understand API. Tagged areas include Company, Video Intelligence, Video Understanding, Video Search, and Transcription.

The Memories catalog on APIs.io includes 1 event-driven AsyncAPI specification.

Memories’ developer surface includes documentation, API reference, getting-started guide, signup flow, pricing, authentication, CLI, and 20 more developer resources.

🌐 Visit website 📡 Source on GitHub

44.9/100 developing ▬ flat Agent 33/100 agent ready Front door AI 5/6 prominent saas Full breakdown ↓
scored 2026-09-25 · rubric v0.23.0

2 APIs

Company Video Intelligence Video Understanding Video Search Transcription Embeddings Multimodal AI Content Moderation AI Agents Machine Learning

Kin Score

Kin Score How this is scored →
scored 2026-09-25 · rubric v0.23.0

Composite quality — 44.9/100 · developing

Contract Quality 10.3 / 19

Developer Ergonomics 8.2 / 15

Access Clarity 3.9 / 15

Operational Transparency 4.1 / 10

Contract Governance 1.6 / 9

Discoverability 5.5 / 8

Regulatory Posture 3.0 / 15

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 33/100 · agent ready

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 7 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 6 / 6

Agent Skills 5 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

The six quality facets above are damped to 75 points between them, because the conditional facet above carries the other 25. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 75% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/memories: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 3

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

Memories Serve API

The Serve API from Memories — 30 operation(s) for serve.

Memories Stream Understanding API

The Stream Understanding API from Memories — 2 operation(s) for stream understanding.

Memories Understand API

The Understand API from Memories — 2 operation(s) for understand.

Open Collections 4

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Memories Platform API (Docs Mapping) Serve API

OPEN COLLECTION

Memories Platform API (Docs Mapping) Serve Stream Understanding API

OPEN COLLECTION

Memories Platform API (Docs Mapping) Serve Understand API

OPEN COLLECTION

Rate Limits 1

Documented rate limits and quota policies.

Memories Rate Limits

4 limits

RATE LIMITS

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Memories Webhooks

ASYNCAPI

Security Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Memories Authentication

apiKey · 1 scheme

SECURITY

Memories Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Memories Trust Center

SOC 2, HIPAA, GDPR

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Memories Agentic Access

34 operations · 20 acting · 1 human-in-the-loop

34 operations · 20 acting

AGENTIC

Resources

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 5

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

AgenticAccess

X-MCPServerCandidate

LLMsTxt

AgentSkill

WellKnown

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Webhooks

ErrorCatalog

Conventions

Lifecycle

Conformance

DataModel

Build 3

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Packages

Packages

CLI

CLI

Access & Security 4

Authentication, authorization, and security posture

TrustCenter

Compliance

Authentication

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

RateLimits

RateLimits

Commercial 1

Pricing, plans, and the legal terms of use

Pricing

Pricing

Company 1

The organization behind the API

Website

Website

Other 1

Properties that don't map to a standard resource type

Overlay

Overlay

Source (apis.yml)

aid: memories
name: Memories
description: 'Memories.ai (MAVI) is a video-intelligence platform that turns raw video into searchable, agent-ready understanding.
  It ships three products on a shared video-understanding stack: Visual Intelligence (stateless REST APIs for transcription,
  captioning, frame description, embeddings, social-media scraping, and real-time audio/video stream moderation via VLMs such
  as Gemini, Nova, and Qwen), Visual Search (an auto-indexed private and public video/image library searchable by text, image,
  or transcript), and Visual Agents (pre-built workflows for video search, AI video editing, and screenplay extraction). The
  platform authenticates with sk-mavi- API keys, bills on a unified per-endpoint credit model, and is HIPAA, SOC 2 Type 2,
  and GDPR compliant. It is a Seedcamp portfolio company.'
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
specificationVersion: '0.23'
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - authentication
  - rate-limits
  - security
  generated: '2026-09-03'
  method: derived
image: https://mintcdn.com/memories/xyhRN3OJaXxxzcxh/logo/logo.png
url: https://raw.githubusercontent.com/api-evangelist/memories/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- seedcamp
tags:
- Company
- Video Intelligence
- Video Understanding
- Video Search
- Transcription
- Embeddings
- Multimodal AI
- Content Moderation
- AI Agents
- Machine Learning
tags_raw:
- Company
- Video Intelligence
- Video Understanding
- Video Search
- Transcription
- Embeddings
- Multimodal AI
- Content Moderation
- AI Agents
- Machine Learning
- Machine-Learning
created: '2026-07-17'
modified: '2026-07-20'
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
apis:
- aid: memories:memories-serve-api
  name: Memories Serve API
  description: The Serve API from Memories — 30 operation(s) for serve.
  humanURL: https://api-tools.memories.ai/visual-search/introduction
  baseURL: https://api.memories.ai
  tags:
  - Serve
  properties:
  - type: OpenAPI
    url: openapi/memories-serve-api-openapi.yml
- aid: memories:memories-stream-understanding-api
  name: Memories Stream Understanding API
  description: The Stream Understanding API from Memories — 2 operation(s) for stream understanding.
  humanURL: https://api-tools.memories.ai/visual-search/introduction
  baseURL: https://api.memories.ai
  tags:
  - Stream Understanding
  properties:
  - type: OpenAPI
    url: openapi/memories-stream-understanding-api-openapi.yml
- aid: memories:memories-understand-api
  name: Memories Understand API
  description: The Understand API from Memories — 2 operation(s) for understand.
  humanURL: https://api-tools.memories.ai/visual-search/introduction
  baseURL: https://api.memories.ai
  tags:
  - Understand
  properties:
  - type: OpenAPI
    url: openapi/memories-understand-api-openapi.yml
common:
- type: TrustCenter
  url: security/memories-trust-center.yml
- type: DeveloperPortal
  url: https://api-platform.memories.ai/
- type: Documentation
  url: https://api-tools.memories.ai/
- type: APIReference
  url: https://api-tools.memories.ai/visual-intelligence/getting-started/overview
- type: GettingStarted
  url: https://api-tools.memories.ai/visual-intelligence/getting-started/introduction
- type: SignUp
  url: https://api-platform.memories.ai/
- type: Pricing
  url: https://api-tools.memories.ai/visual-search/pricing
- type: GitHubOrganization
  url: https://github.com/Memories-ai-labs
- type: Compliance
  url: https://memories.ai/security
- type: Authentication
  url: authentication/memories-authentication.yml
- type: AgenticAccess
  url: agentic-access/memories-agentic-access.yml
- type: Packages
  url: packages/memories-packages.yml
- type: CLI
  url: cli/memories-cli.yml
- type: X-MCPServerCandidate
  url: mcp/memories-mcp.yml
  note: 'Renamed from MCPServer 2026-09-03 (roadmap#247): the manifest self-describes as status: candidate — a tool list derived
    from the published API contracts, not an existing server. The scorer already read the manifest and reported mcp_server
    correctly; the MCPServer type was crediting the artifact-type surfaces with a server that does not exist.'
- type: LLMsTxt
  url: llms/memories-llms.txt
- type: AgentSkill
  url: skills/_index.yml
- type: Webhooks
  url: asyncapi/memories-webhooks.yml
- type: ErrorCatalog
  url: errors/memories-error-codes.yml
- type: Conventions
  url: conventions/memories-conventions.yml
- type: RateLimits
  url: rate-limits/memories-rate-limits.yml
- type: Lifecycle
  url: lifecycle/memories-lifecycle.yml
- type: Conformance
  url: conformance/memories-conformance.yml
- type: DataModel
  url: data-model/memories-data-model.yml
- type: DomainSecurity
  url: security/memories-domain-security.yml
- type: WellKnown
  url: well-known/memories-well-known.yml
- type: Overlay
  url: overlays/memories-platform-overlay.yaml
- type: Website
  url: http://memories.ai
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 21
  pass: local-v1

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/memories"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/memories/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/memories/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.