poolside

poolside builds open-weight foundation models and the systems that refine them for agentic software engineering. Its Laguna model family (Laguna XS 2.1, a 33B on-device model, and Laguna M.1, a 225B model with a 256K context window) is served through an OpenAI-compatible inference API at inference.poolside.ai, the hosted Poolside Platform, OpenRouter, and self-managed on-premises / cloud Kubernetes deployments (Amazon EKS, OpenShift, upstream Kubernetes). Developers work with the models through the `pool` Agent CLI, editor and coding-agent integrations (VS Code, JetBrains, Neovim, Zed, Cline, Goose, GitHub Copilot), the Agent Client Protocol, MCP servers, and reusable Skills / AGENTS.md instructions. poolside targets secure, self-hosted enterprise and government software engineering and is backed by SoftBank Vision Fund.

poolside publishes 1 API on the APIs.io network. Tagged areas include Company, Enterprise, Artificial Intelligence, Machine-Learning, and Foundation Models.

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

🌐 Visit website 📡 Source on GitHub

33.7/100 thin ▬ flat Agent 16/100 agent aware Full breakdown ↓
scored 2026-08-21 · rubric v0.12.0

AccessSelf serve

1 APIs

Company Enterprise Artificial Intelligence Machine-Learning Foundation Models Coding Assistant Developer Tools LLM Agents Code Generation Inference OpenAI-Compatible

Kin Score

Kin Score How this is scored →
scored 2026-08-21 · rubric v0.12.0

Composite quality — 33.7/100 · thin

Contract Quality 0.0 / 25

Developer Ergonomics 11.3 / 20

Access Clarity 7.1 / 20

Operational Transparency 4.4 / 13

Contract Governance 2.2 / 12

Discoverability 8.7 / 10

Agent readiness — 16/100 · agent aware

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 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 3 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

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/poolside: 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.

Get Started 5

Portal, sign-up, and the first successful call

DeveloperPortal

GettingStarted

Quickstart

SignUp

Login

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

WellKnown

WellKnown

AgentSkill

AgentSkill

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

Conventions

Conformance

Lifecycle

ErrorCatalog

Build 2

SDKs, sample code, and the tooling you integrate with

CLI

CLI

Packages

Packages

Access & Security 6

Authentication, authorization, and security posture

TrustCenter

TrustCenter

SecurityTxt

SecurityTxt

Security

Security

VulnerabilityDisclosure

VulnerabilityDisclosure

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 4

Status, limits, changes, and where to get help

Support

ChangeLog

Deprecation

ChangeLog

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 1

The organization behind the API

Blog

Blog

Source (apis.yml)

aid: poolside
name: poolside
description: poolside builds open-weight foundation models and the systems that refine them for agentic software engineering.
  Its Laguna model family (Laguna XS 2.1, a 33B on-device model, and Laguna M.1, a 225B model with a 256K context window)
  is served through an OpenAI-compatible inference API at inference.poolside.ai, the hosted Poolside Platform, OpenRouter,
  and self-managed on-premises / cloud Kubernetes deployments (Amazon EKS, OpenShift, upstream Kubernetes). Developers work
  with the models through the `pool` Agent CLI, editor and coding-agent integrations (VS Code, JetBrains, Neovim, Zed, Cline,
  Goose, GitHub Copilot), the Agent Client Protocol, MCP servers, and reusable Skills / AGENTS.md instructions. poolside targets
  secure, self-hosted enterprise and government software engineering and is backed by SoftBank Vision Fund.
url: https://raw.githubusercontent.com/api-evangelist/poolside/refs/heads/main/apis.yml
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
image: https://poolside.ai/og/og-home.png
x-type: company
x-source: vc-portfolio
x-backed-by:
- softbank-vision-fund
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-20'
tags:
- Company
- Enterprise
- Artificial Intelligence
- Machine-Learning
- Foundation Models
- Coding Assistant
- Developer Tools
- LLM
- Agents
- Code Generation
- Inference
- OpenAI-Compatible
tags_raw:
- Company
- Enterprise
- Artificial Intelligence
- Machine Learning
- Foundation Models
- Coding Assistant
- Developer Tools
- LLM
- Agents
- Code Generation
- Inference
- OpenAI Compatible
apis:
- name: Poolside API
  description: OpenAI-compatible inference API for poolside's Laguna agentic-coding models. Send chat-completion and model-listing
    requests from your own tools, scripts, and applications using the OpenAI SDK by switching the base URL and API key.
  humanURL: https://docs.poolside.ai/api/overview
  baseURL: https://inference.poolside.ai/v1
  tags:
  - Inference
  - LLM
  - OpenAI-Compatible
  - Chat Completions
  tags_raw:
  - Inference
  - LLM
  - OpenAI Compatible
  - Chat Completions
  properties:
  - type: Documentation
    url: https://docs.poolside.ai/api/overview
  - type: APIReference
    url: https://docs.poolside.ai/api/openai-api-examples
  - type: Authentication
    url: authentication/poolside-authentication.yml
  - type: Conventions
    url: conventions/poolside-conventions.yml
  - type: Conformance
    url: conformance/poolside-conformance.yml
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 16
  pass: local-v1
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: DeveloperPortal
  url: https://platform.poolside.ai
- type: Documentation
  url: https://docs.poolside.ai
- type: APIReference
  url: https://docs.poolside.ai/api/openai-api-examples
- type: GettingStarted
  url: https://docs.poolside.ai/get-started/quickstart
- type: Quickstart
  url: https://docs.poolside.ai/get-started/quickstart
- type: SignUp
  url: https://platform.poolside.ai
- type: Login
  url: https://docs.poolside.ai/get-started/log-in
- type: Support
  url: https://docs.poolside.ai/support/overview
- type: Blog
  url: https://poolside.ai/blog
- type: TermsOfService
  url: https://docs.poolside.ai/legal/end-user-license-agreement
- type: PrivacyPolicy
  url: https://docs.poolside.ai/legal/privacy-policy
- type: TrustCenter
  url: https://trust.poolside.ai/
- type: ChangeLog
  url: https://docs.poolside.ai/release-notes/overview
- type: LLMsTxt
  url: llms/poolside-llms.txt
- type: WellKnown
  url: well-known/poolside-well-known.yml
- type: SecurityTxt
  url: well-known/poolside-security.txt
- type: Security
  url: https://poolside.ai/.well-known/security.txt
- type: VulnerabilityDisclosure
  url: security/poolside-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/poolside-domain-security.yml
- type: Authentication
  url: authentication/poolside-authentication.yml
- type: Conventions
  url: conventions/poolside-conventions.yml
- type: Conformance
  url: conformance/poolside-conformance.yml
- type: Lifecycle
  url: lifecycle/poolside-lifecycle.yml
- type: Deprecation
  url: lifecycle/poolside-lifecycle.yml
- type: CLI
  url: cli/poolside-cli.yml
- type: Packages
  url: packages/poolside-packages.yml
- type: ChangeLog
  url: changelog/poolside-changelog.yml
- type: AgentSkill
  url: skills/_index.yml
- type: ErrorCatalog
  url: errors/poolside-problem-types.yml

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/poolside"

All providers

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

Every operation they expose

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

How their score was established

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

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

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

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