RunAnywhere

RunAnywhere is a Y Combinator (W2026) infrastructure company building the layer for deploying fast, private, multimodal AI on-device at scale. It ships one open-source C++ core runtime with native bindings for Swift, Kotlin, React Native, Flutter, and the browser, plus hand-written GPU/NPU inference engines (MetalRT for Apple GPUs, QHexRT for Qualcomm Hexagon NPUs) that run LLM, VLM, speech-to-text, text-to-speech, and embedding workloads locally. The SDKs handle model delivery, extraction, storage management, versioning, and observability, and support hybrid routing that tries on-device inference first before optionally falling back to the cloud. A hosted control plane (api.runanywhere.ai) manages model delivery and configuration via API key.

RunAnywhere publishes 1 API on the APIs.io network. Tagged areas include Company, On-Device AI, Inference, Machine Learning, and SDK.

RunAnywhere’s developer surface includes documentation, getting-started guide, engineering blog, support, CLI, and 8 more developer resources.

🌐 Visit website 📡 Source on GitHub

22.1/100 emerging ▬ flat Agent 0/100 human only Full breakdown ↓
scored 2026-07-27 · rubric v0.5

1 APIs

CompanyOn-Device AIInferenceMachine LearningSDKMobileEdge AILLMSpeechY Combinator

Kin Score

Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5

Composite quality — 22.1/100 · emerging

Contract Quality 0.0 / 25

Developer Ergonomics 9.6 / 20

Commercial Clarity 2.6 / 20

Operational Transparency 0.7 / 13

Governance 0.0 / 12

Discoverability 9.3 / 10

Agent readiness — 0/100 · human only

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 15

MCP Server 0 / 12

Machine-Readable Auth 0 / 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 0 / 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/runanywhere: 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 3

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

Login

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt

LLMsTxt

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

Packages

SDKs

CLI

Access & Security 1

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Operate 1

Status, limits, changes, and where to get help

Support

Support

Company 2

The organization behind the API

Website

Website

Blog

Blog

Source (apis.yml)

aid: runanywhere
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source: []
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/runanywhere.png
name: RunAnywhere
description: RunAnywhere is a Y Combinator (W2026) infrastructure company building the layer for deploying fast, private,
  multimodal AI on-device at scale. It ships one open-source C++ core runtime with native bindings for Swift, Kotlin, React
  Native, Flutter, and the browser, plus hand-written GPU/NPU inference engines (MetalRT for Apple GPUs, QHexRT for Qualcomm
  Hexagon NPUs) that run LLM, VLM, speech-to-text, text-to-speech, and embedding workloads locally. The SDKs handle model
  delivery, extraction, storage management, versioning, and observability, and support hybrid routing that tries on-device
  inference first before optionally falling back to the cloud. A hosted control plane (api.runanywhere.ai) manages model delivery
  and configuration via API key.
url: https://raw.githubusercontent.com/api-evangelist/runanywhere/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Company
- On-Device AI
- Inference
- Machine Learning
- SDK
- Mobile
- Edge AI
- LLM
- Speech
- Y Combinator
apis:
- name: RunAnywhere Control Plane API
  description: Hosted control plane the RunAnywhere SDKs talk to for model delivery, extraction, versioning, and configuration.
    Authenticated with an API key supplied at SDK initialization. No public OpenAPI is published as of 2026-07-21 (the docs
    api-reference exposes only the default Mintlify sample), so no spec is captured.
  humanURL: https://docs.runanywhere.ai/quickstart
  baseURL: https://api.runanywhere.ai
  properties:
  - type: Authentication
    url: https://docs.runanywhere.ai/quickstart
common:
- type: DomainSecurity
  url: security/runanywhere-domain-security.yml
- type: Website
  url: https://www.runanywhere.ai/
- type: DeveloperPortal
  url: https://docs.runanywhere.ai
- type: Documentation
  url: https://docs.runanywhere.ai
- type: GettingStarted
  url: https://docs.runanywhere.ai/quickstart
- type: GitHubOrganization
  url: https://github.com/RunanywhereAI
- type: Blog
  url: https://www.runanywhere.ai/blog
- type: Login
  url: https://runanywhere-frontend-production.up.railway.app/login
- type: Support
  url: mailto:san@runanywhere.ai
- type: Packages
  url: packages/runanywhere-packages.yml
- type: SDKs
  url: packages/runanywhere-packages.yml
- type: CLI
  url: cli/runanywhere-cli.yml
- type: LLMsTxt
  url: llms/runanywhere-llms.txt
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 5
  pass: local-v1