Flow AI

Flow AI builds infrastructure for embedding schema-aware, deterministic AI agents directly inside analytical SaaS products. Its flagship flowai-harness is a Rust-native runtime with a Python SDK for building production-grade data agents on top of your own data product, organized around five primitives - a data catalog agents use to resolve intent, typed plans and actions executed as auditable state machines with human approval gates, an embedded runtime, Studio (a local UI to run, debug, and evaluate agents), and self-improvement. It runs inside your infrastructure with your own model keys (OpenAI, Anthropic, Gemini, Llama, Mistral, Qwen) and warehouse (Postgres, Snowflake, BigQuery, Databricks, DuckDB). The team also publishes the open Flow Judge LLM-as-a-judge evaluation model and the flow-eval evaluation engine.

Flow AI is profiled on the APIs.io network. Tagged areas include Company, Artificial Intelligence, AI Agents, Agent Infrastructure, and LLM Evaluation.

Flow AI’s developer surface includes documentation, API reference, getting-started guide, pricing, engineering blog, support, YouTube channel, and 20 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

37.5/100 thin ▬ flat Agent 3/100 human only Front door AI 6/6 dominant Heartbeat 34/100 slowing saas Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →

AccessFreemiumSelf serve⚡ Free to try

0 APIs 1 MCP Servers 1 Agent Skills

Company Artificial Intelligence AI Agents Agent Infrastructure LLM Evaluation Data Runtime SDK MCP Analytics

Kin Score

Kin Score How this is scored →
scored 2026-11-06 · rubric v0.27.0

Composite quality — 37.5/100 · thin

Contract Quality 0.0 / 21

Developer Ergonomics 13.7 / 17

Access Clarity 8.5 / 17

Operational Transparency 2.0 / 11

Contract Governance 1.9 / 10

Discoverability 4.7 / 9

Regulatory Posture 3.5 / 15

Agent readiness — 3/100 · 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 0 / 7

Typed Event Surface 0 / 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

Pagination 5 / 5

Distinct Operations 3 / 3

MCP Tool Quality 6 / 6

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/.

Show this score on your site.

It updates itself when the score changes. Paste this where you link to your API docs:

<a href="https://apis.io/providers/flow-ai/"><img src="https://apis.io/badge/flow-ai/card.svg" alt="Flow AI on APIs.io — Kin Score by API Evangelist"></a>

Other styles, a README pill and a shields.io endpoint are on the badge page.

Raise your score.

Agent readiness — checks not met, largest first (exact, from this profile):

Machine-Readable Contract +18 pts — api_specs includes an OpenAPI document
MCP Server +12 pts — deployment.mode + probe verdict on the mcp/ manifest, not the pointer; an unprobed slug falls back to authorship
Agentic Access Contract +10 pts — agentic_access artifact present (x-agentic-access), graded by author
Idempotency +9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
Stable Error Semantics +8 pts — OpenAPI $refs a shared error schema across 4xx/5xx responses (verified), else common[].type includes ErrorCatalog / ErrorCodes / DeclineCodes
A2A Agent Card +8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0

11 more unmet checks in the Agent Readiness table above.

Kin Score — facets with the most composite points still available (weight × headroom):

Contract Quality scores 0.0 — up to +25.0 composite points
Operational Transparency scores 18.4 — up to +10.6 composite points
Access Clarity scores 50.0 — up to +10.0 composite points

Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.

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 the provider profile at artifacts.apis.io/flow-ai/apis.yml: open an issue on github.com/api-evangelist/flow-ai to ask a question or point us at an artifact you publish. 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.

Model Context Protocol (MCP)

tagged — the provider's own APIs.json carries the standard as a tag; implementation not verified

MCP Servers 1

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

Flow AI MCP Server

flowai-harness can expose its runtime tools as Model Context Protocol (MCP) servers, so an MCP-aware client (Claude, IDEs, agents) can call the data-agent tools defined in a Flo...

MCP SERVER

Agent Skills 1

Packaged agent skills for driving this provider's APIs from an AI assistant.

Build a coordinator-planner-executor data agent

AGENT SKILL

Flow AI API pricing

Prices published by Flow AI, read 2026-10-07 from flow-ai.com/pricing.

Plan	Price
Development	$0 Includes: Build and prototype locally. Source-available. Local Dev Studio, five primitives, local + scheduled
Production	Custom Includes: Run in production, inside your own infrastructure. Multi-user Studio with SSO, RBAC, audit log; sove

Plan details, limits and sources →

Pricing Plans 1

Published pricing tiers and plan structures.

Flow Ai Plans Pricing

2 plans

PLANS

Security Posture 2

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

Flow Ai Authentication

provider-api-key/sso · 2 schemes

SECURITY

Flow Ai Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

Sandbox

Sandbox

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 2

Pagination, idempotency, versioning, errors, and events

Conventions

Conventions

Conformance

Conformance

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

Packages

SDKs

CLI

Access & Security 3

Authentication, authorization, and security posture

Authentication

Authentication

Compliance

Compliance

DomainSecurity

DomainSecurity

Learn 1

Tutorials, courses, talks, and written guidance

YouTube

YouTube

Operate 2

Status, limits, changes, and where to get help

Support

Support

ChangeLog

ChangeLog

Commercial 3

Pricing, plans, and the legal terms of use

Plans

Plans

Pricing

Pricing

PrivacyPolicy

PrivacyPolicy

Company 4

The organization behind the API

Website

Website

Blog

Blog

LinkedIn

Twitter

Twitter

Source (apis.yml)

aid: flow-ai
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: false
  label: Hosted service · you call their endpoint
  confidence: medium
  source:
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: freemium
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Freemium · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  - security
  - sandbox
  generated: '2026-11-06'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/flow-ai.png
name: Flow AI
description: Flow AI builds infrastructure for embedding schema-aware, deterministic AI agents directly inside analytical
  SaaS products. Its flagship flowai-harness is a Rust-native runtime with a Python SDK for building production-grade data
  agents on top of your own data product, organized around five primitives - a data catalog agents use to resolve intent,
  typed plans and actions executed as auditable state machines with human approval gates, an embedded runtime, Studio (a local
  UI to run, debug, and evaluate agents), and self-improvement. It runs inside your infrastructure with your own model keys
  (OpenAI, Anthropic, Gemini, Llama, Mistral, Qwen) and warehouse (Postgres, Snowflake, BigQuery, Databricks, DuckDB). The
  team also publishes the open Flow Judge LLM-as-a-judge evaluation model and the flow-eval evaluation engine.
url: https://raw.githubusercontent.com/api-evangelist/flow-ai/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- project-a
- seedcamp
- lifeline
- moonfire
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-19'
tags:
- Company
- Artificial Intelligence
- AI Agents
- Agent Infrastructure
- LLM Evaluation
- Data
- Runtime
- SDK
- MCP
- Analytics
tags_raw:
- Company
- Artificial Intelligence
- AI Agents
- Agent Infrastructure
- LLM Evaluation
- Data
- Runtime
- SDK
- Model Context Protocol
- Analytics
apis: []
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Plans
  url: plans/flow-ai-plans-pricing.yml
- type: Website
  url: https://flow-ai.com
- type: DeveloperPortal
  url: https://flow-ai.com/docs
- type: Documentation
  url: https://flow-ai.com/docs
- type: APIReference
  url: https://flow-ai.com/docs/reference
- type: GettingStarted
  url: https://flow-ai.com/docs/quickstart
- type: Pricing
  url: https://flow-ai.com/pricing
- type: Blog
  url: https://flow-ai.com/blog
- type: GitHubOrganization
  url: https://github.com/flowaicom
- type: PrivacyPolicy
  url: https://flow-ai.com/legal
- type: Support
  url: mailto:hello@flow-ai.com
- type: LinkedIn
  url: https://linkedin.com/company/flowaicom
- type: Twitter
  url: https://x.com/flowaicom
- type: YouTube
  url: https://youtube.com/@flowaicom
- type: LLMsTxt
  url: llms/flow-ai-llms.txt
- type: Packages
  url: packages/flow-ai-packages.yml
- type: SDKs
  url: packages/flow-ai-packages.yml
- type: MCPServer
  url: mcp/flow-ai-mcp.yml
- type: AgentSkill
  url: skills/_index.yml
- type: ChangeLog
  url: changelog/flow-ai-changelog.yml
- type: CLI
  url: cli/flow-ai-cli.yml
- type: Authentication
  url: authentication/flow-ai-authentication.yml
- type: Conventions
  url: conventions/flow-ai-conventions.yml
- type: Sandbox
  url: sandbox/flow-ai-sandbox.yml
- type: Conformance
  url: conformance/flow-ai-conformance.yml
- type: Compliance
  url: https://flow-ai.com/legal
- type: DomainSecurity
  url: security/flow-ai-domain-security.yml
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence

Flow AI API — frequently asked questions

How do I authenticate with the Flow AI API?

Flow AI uses bearer-token authentication (provider-api-key/sso · 2 schemes). The details are profiled on APIs.io as Flow Ai Authentication.

How much does the Flow AI API cost?

Flow AI publishes its prices; its Development plan is $0 as of 2026-10-07. APIs.io lists 2 pricing plans for Flow AI, with each plan's price, limits and inclusions under Pricing on this page.

Does Flow AI have an MCP server?

Yes. APIs.io lists 1 MCP server for Flow AI: flowai-harness can expose its runtime tools as Model Context Protocol (MCP) servers, so an MCP-aware client (Claude, IDEs, agents) can call the data-agent tools defined in a Flow AI runtime. This is a

Is the Flow AI API ready for AI agents?

Flow AI has a Kin Score of 37.5 out of 100 (thin) and an Agent Readiness score of 3.4 (human-only), scored by API Evangelist on 2026-11-06.

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/flow-ai"

All providers

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

Every operation they expose

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

How their score was established

curl "https://apis.io/api/v1/providers/flow-ai/evidence"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

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.