AgentSea

AgentSea is an open-source agent development kit (ADK) for building agentic AI applications, authored by Michael Fatoki-Bello and published under the lovekaizen GitHub account. It ships as twenty TypeScript/Node packages on npm under the @lov3kaizen/agentsea-* scope and, separately, as fourteen native Elixir/OTP libraries on Hex (agentsea_*). The framework covers multi-provider LLM access, agent and crew orchestration, sequential/parallel workflows, memory, embeddings, guardrails, evaluation, red-teaming, cost tracking, semantic caching, document ingest, prompt management, browser and computer use, and voice (TTS/STT), plus a Model Context Protocol client and Agentic Commerce Protocol tooling. AgentSea is self-hosted software rather than a vendor-operated API - its HTTP surface (an /agents REST + Server-Sent Events + WebSocket API via the NestJS module, and an OpenAI-compatible /v1/chat/completions LLM gateway) runs inside the consumer's own deployment. MIT licensed.

AgentSea is listed with 2 APIs on the APIs.io network. Tagged areas include Company, Artificial Intelligence, AI Agents, Agent Orchestration, and LLM.

AgentSea’s developer surface includes documentation, API reference, getting-started guide, support, changelog, CLI, authentication, and 16 more developer resources.

🌐 Visit website 📡 Source on GitHub

25.0/100 emerging ▬ flat Agent 5/100 human only Front door AI 6/6 dominant open core · MIT Full breakdown ↓
scored 2026-10-17 · rubric v0.24.0

2 APIs

Company Artificial Intelligence AI Agents Agent Orchestration LLM MCP Agentic Commerce Open Source Developer Tools SDK TypeScript Elixir Voice

Kin Score

Kin Score How this is scored →
scored 2026-10-17 · rubric v0.24.0

Composite quality — 25.0/100 · emerging

Contract Quality 0.0 / 21

Developer Ergonomics 11.7 / 17

Access Clarity 0.0 / 17

Operational Transparency 2.0 / 11

Contract Governance 1.9 / 10

Discoverability 5.6 / 9

Regulatory Posture 2.3 / 15

Agent readiness — 5/100 · human only

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 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 could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.

The six quality facets above are damped to 85 points between them, because the conditional facet above carries the other 15. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 85% 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/agentsea: 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 →

Standards implemented 1

Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.

The OpenAI Interface

prose — states compatibility; nothing published to check it against

2 core of 338 operations graded · api-commons/models

APIs 2

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

AgentSea Agent REST API

HTTP surface exposed by the AgentSea NestJS module (@lov3kaizen/agentsea-nestjs) when enableRestApi/enableWebSocket are set. Documented operations are GET /agents, GET /agents/:...

AgentSea LLM Gateway

OpenAI-compatible HTTP gateway shipped as @lov3kaizen/agentsea-gateway (and as the Elixir agentsea_web Phoenix app). Run createHTTPServer/startServer and POST /v1/chat/completio...

Pricing Plans 1

Published pricing tiers and plan structures.

Agentsea Plans Pricing

0 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Agentsea Rate Limits

0 limits

RATE LIMITS

Security Posture 2

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

Agentsea Authentication

2 schemes

SECURITY

Agentsea Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 2

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt

LLMsTxt

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

Components

Conventions

Conformance

Lifecycle

Build 5

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

SourceCode

Packages

SDKs

CLI

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 4

Status, limits, changes, and where to get help

Support

ChangeLog

ChangeLog

RateLimits

Commercial 2

Pricing, plans, and the legal terms of use

License

License

Plans

Plans

Company 1

The organization behind the API

Website

Website

Source (apis.yml)

aid: agentsea
name: AgentSea
description: AgentSea is an open-source agent development kit (ADK) for building agentic AI applications, authored by Michael
  Fatoki-Bello and published under the lovekaizen GitHub account. It ships as twenty TypeScript/Node packages on npm under
  the @lov3kaizen/agentsea-* scope and, separately, as fourteen native Elixir/OTP libraries on Hex (agentsea_*). The framework
  covers multi-provider LLM access, agent and crew orchestration, sequential/parallel workflows, memory, embeddings, guardrails,
  evaluation, red-teaming, cost tracking, semantic caching, document ingest, prompt management, browser and computer use,
  and voice (TTS/STT), plus a Model Context Protocol client and Agentic Commerce Protocol tooling. AgentSea is self-hosted
  software rather than a vendor-operated API - its HTTP surface (an /agents REST + Server-Sent Events + WebSocket API via
  the NestJS module, and an OpenAI-compatible /v1/chat/completions LLM gateway) runs inside the consumer's own deployment.
  MIT licensed.
deliveryModel:
  model: open-core
  license: MIT
  license_evidence:
    repo: lovekaizen/agentsea
    spdx: MIT
    stars: 22
  open_source: true
  commercial: true
  callable_host: false
  label: Open core · an OSS project plus a commercial hosted product
  confidence: medium
  source:
  - pricing
  - repository-license
  generated: '2026-09-25'
  method: derived
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://agentsea.dev/opengraph-image
url: https://raw.githubusercontent.com/api-evangelist/agentsea/refs/heads/main/apis.yml
x-type: company
x-source: harvest:manual
specificationVersion: '0.20'
created: '2026-08-24'
modified: '2026-08-24'
tags:
- Company
- Artificial Intelligence
- AI Agents
- Agent Orchestration
- LLM
- MCP
- Agentic Commerce
- Open Source
- Developer Tools
- SDK
- TypeScript
- Elixir
- Voice
tags_raw:
- Company
- Artificial Intelligence
- AI Agents
- Agent Orchestration
- Large Language Models
- Model Context Protocol
- Agentic Commerce
- Open Source
- Developer Tools
- SDKs
- TypeScript
- Elixir
- Voice
- Open-Source
apis:
- aid: agentsea:agent-rest-api
  name: AgentSea Agent REST API
  description: 'HTTP surface exposed by the AgentSea NestJS module (@lov3kaizen/agentsea-nestjs) when enableRestApi/enableWebSocket
    are set. Documented operations are GET /agents, GET /agents/:name, POST /agents/:name/execute, POST /agents/:name/stream
    (Server-Sent Events), and DELETE /agents/:name/conversations/:id, plus a Socket.IO gateway on the /agents namespace with
    execute / getAgent / listAgents events. Self-hosted: the host is the consumer''s own deployment, so the base is templated
    rather than vendor-operated.'
  humanURL: https://www.agentsea.dev/api/
  baseURL: https://{your-agentsea-host}
  tags:
  - AI Agents
  - Agent Orchestration
  - Server-Sent Events
  - WebSocket
  tags_raw:
  - AI Agents
  - Agent Orchestration
  - Server-Sent Events
  - WebSockets
  properties:
  - type: APIReference
    url: https://www.agentsea.dev/api/
  - type: Documentation
    url: https://www.agentsea.dev/docs/nestjs/
- aid: agentsea:llm-gateway
  name: AgentSea LLM Gateway
  description: 'OpenAI-compatible HTTP gateway shipped as @lov3kaizen/agentsea-gateway (and as the Elixir agentsea_web Phoenix
    app). Run createHTTPServer/startServer and POST /v1/chat/completions with any OpenAI SDK; virtual models "best", "cheapest"
    and "fastest" route across configured providers with load balancing, failover, circuit breaking, caching and cost optimization.
    Self-hosted: the base URL is the consumer''s own deployment.'
  humanURL: https://www.agentsea.dev/docs/gateway/
  baseURL: https://{your-agentsea-gateway-host}/v1
  tags:
  - LLM
  - Gateways
  - Routing
  tags_raw:
  - Large Language Models
  - Gateway
  - Routing
  properties:
  - type: Documentation
    url: https://www.agentsea.dev/docs/gateway/
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: DomainSecurity
  url: security/agentsea-domain-security.yml
- type: Website
  url: https://agentsea.dev
- type: DeveloperPortal
  url: https://www.agentsea.dev/docs/
- type: Documentation
  url: https://www.agentsea.dev/docs/
- type: APIReference
  url: https://www.agentsea.dev/api/
- type: GettingStarted
  url: https://www.agentsea.dev/docs/quick-start/
- type: GitHubOrganization
  url: https://github.com/lovekaizen/agentsea
- type: SourceCode
  url: https://github.com/lovekaizen/agentsea
- type: Support
  url: https://github.com/lovekaizen/agentsea/issues
- type: ChangeLog
  url: https://github.com/lovekaizen/agentsea/releases
- type: License
  url: https://github.com/lovekaizen/agentsea/blob/main/LICENSE
- type: Packages
  url: packages/agentsea-packages.yml
- type: SDKs
  url: packages/agentsea-packages.yml
- type: CLI
  url: cli/agentsea-cli.yml
- type: Components
  url: components/agentsea-components.yml
- type: LLMsTxt
  url: llms/agentsea-llms.txt
- type: Authentication
  url: authentication/agentsea-authentication.yml
- type: Conventions
  url: conventions/agentsea-conventions.yml
- type: Conformance
  url: conformance/agentsea-conformance.yml
- type: Lifecycle
  url: lifecycle/agentsea-lifecycle.yml
- type: ChangeLog
  url: changelog/agentsea-changelog.yml
- type: Plans
  url: plans/agentsea-plans-pricing.yml
- type: RateLimits
  url: rate-limits/agentsea-rate-limits.yml
x-enrichment:
  date: '2026-08-24'
  status: enriched
  artifacts_added: 14
  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/agentsea"

All providers

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

Every operation they expose

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

How their score was established

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