Flow AI website screenshot

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 19 more developer resources.

🌐 Visit website 📡 Source on GitHub
32.7/100 thin ▬ flat Agent 26/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
0 APIs 1 MCP Servers
CompanyArtificial IntelligenceAI AgentsAgent InfrastructureLLM EvaluationDataRuntimeSDKModel Context ProtocolAnalytics

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 32.7/100 · thin
Contract Quality 0.0 / 25
Developer Ergonomics 17.4 / 20
Commercial Clarity 5.8 / 20
Operational Transparency 2.7 / 13
Governance 0.0 / 12
Discoverability 6.8 / 10
Agent readiness — 26/100 · 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 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
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/flow-ai: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

MCP Servers 1

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

flow-ai-mcp.yml

MCP SERVER

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
GitHubOrganization
 Packages
Packages
 SDKs
SDKs
 CLI
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 2

Pricing, plans, and the legal terms of use

Pricing
Pricing
 PrivacyPolicy
PrivacyPolicy

Company 4

The organization behind the API

Website
Website
 Blog
Blog
 LinkedIn
LinkedIn
 Twitter
Twitter

Source (apis.yml)

apis.yml Raw ↑ 
aid: flow-ai
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://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: '0.20'
created: '2026-07-17'
modified: '2026-07-19'
tags:
- 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: 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